[ { "full_name": "watt-mind/pii-guard", "html_url": "https://github.com/watt-mind/pii-guard", "track": "Push the Frontier", "domain": "Developer Tooling, Infra & Security", "summary": "Privacy gateway that replaces PII with reversible placeholders for agents", "readme_summary": "Intercepts prompts to replace personal data with reversible placeholders before leaving network. Python gateway with hosted mode and CI. Built on Meta open models to de-identify emails and rehydrate answers locally.", "tech_highlights": [ "Meta Open Models", "PII Placeholder Gateway", "Python + Docker" ], "created_at": "2026-10-26T20:16:07Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 431, "commits_before_window": 0, "prs_total": 471, "prs_merged": 455, "is_preexisting": false, "has_docker": true, "has_tests": true, "has_src": true, "has_ci": true, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": true, "has_eval_benchmarks": true, "has_setup_guide": true, "has_video_demo": true, "video_urls": [ "https://youtu.be/Lsr74ddhxRo" ], "has_live_deploy": true, "live_urls": [ "https://guard.watt-mind.com/" ], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 9, "score_impact": 3.0, "score_meta_tooling": 2.5, "score_tech_depth": 2.0, "score_demo": 2.5, "score_total": 10.0, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "High-impact domain", "+0.4" ], [ "Eval & benchmark proof", "+0.3" ], [ "Docker packaging", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ], [ "Open-weights / fine-tuning", "+0.5" ], [ "Published HF Hub weights", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (431)", "+0.6" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Agent / eval harness", "+0.2" ], [ "Automated CI workflow", "+0.2" ], [ "PR review workflow (455 PRs)", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Video walkthrough", "+1.1" ], [ "Reproducible setup guide", "+0.4" ], [ "Live web deployment", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 1, "is_new": false, "commits_delta": 214, "rank_delta": 1, "commits_delta_last_run": 0 }, { "full_name": "ta-amps/agora-public-overview-architecture-setup-and-contribution", "html_url": "https://github.com/ta-amps/agora-public-overview-architecture-setup-and-contribution", "track": "Push the Frontier", "domain": "Developer Tooling, Infra & Security", "summary": "Durable task queue and hub for agent swarms with public-good showcase", "readme_summary": "Unifies durable task queue Tessera, Product Hub Agora, and Eranos marketplace for agent work. Docker/Makefile with evals and architecture specs. Uses Meta AI open-weights stack for durable pull-based agent orchestration.", "tech_highlights": [ "Meta Open-Weights", "Durable Task Queue", "Docker + Eval Harness" ], "created_at": "2026-10-29T13:06:17Z", "is_multi_repo": true, "repo_count": 6, "linked_repos": [ { "full_name": "ta-amps/agora-public-overview-architecture-setup-and-contribution", "commits_in_window": 128, "prs_merged": 39, "prs_total": 39, "has_tests": true, "has_docker": true }, { "full_name": "ta-amps/eranos-public-marketplace-for-public-good-token-burn", "commits_in_window": 80, "prs_merged": 17, "prs_total": 17, "has_tests": true, "has_docker": true }, { "full_name": "ta-amps/tessera-infrastructure-work-and-storage-engine", "commits_in_window": 138, "prs_merged": 24, "prs_total": 24, "has_tests": true, "has_docker": true }, { "full_name": "ta-amps/herma-infrastructure-shim-for-intelligent-agents", "commits_in_window": 70, "prs_merged": 21, "prs_total": 21, "has_tests": true, "has_docker": true }, { "full_name": "ta-amps/seed-packs-library-of-nouns-and-verbs", "commits_in_window": 104, "prs_merged": 24, "prs_total": 24, "has_tests": true, "has_docker": true }, { "full_name": "ta-amps/ta-amps-hackathon", "commits_in_window": 31, "prs_merged": 11, "prs_total": 11, "has_tests": true, "has_docker": true } ], "commits_in_window": 551, "commits_before_window": 0, "prs_total": 136, "prs_merged": 136, "is_preexisting": false, "has_docker": true, "has_tests": true, "has_src": true, "has_ci": true, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": true, "has_eval_benchmarks": true, "has_setup_guide": true, "has_video_demo": true, "video_urls": [ "https://agora.ta-amps.workers.dev/film/", "https://agora.ta-amps.workers.dev/video/2026-10-31/full-v6/eranos-3m.mp4" ], "has_live_deploy": true, "live_urls": [ "https://eranos.ta-amps.workers.dev", "https://agora.ta-amps.workers.dev/", "https://agora.ta-amps.workers.dev/video/2026-10-31/full-v6/eranos-3m.mp4", "https://agora.ta-amps.workers.dev/judges/", "https://agora.ta-amps.workers.dev/library/#explorer", "https://agora.ta-amps.workers.dev/decks/", "https://agora.ta-amps.workers.dev/use-cases/", "https://agora.ta-amps.workers.dev/learning/", "https://agora.ta-amps.workers.dev/library/", "https://agora.ta-amps.workers.dev/decks/roll-your-own/#connect", "https://agora.ta-amps.workers.dev/deploy/#partners", "https://agora.ta-amps.workers.dev/decks/overview-and-architecture/", "https://agora.ta-amps.workers.dev/decks/public-good-marketplace/", "https://agora.ta-amps.workers.dev/decks/roll-your-own/", "https://agora.ta-amps.workers.dev/decks/server-workers/", "https://agora.ta-amps.workers.dev/decks/continuous-learning/", "https://agora.ta-amps.workers.dev/decks/earlier-drafts/", "https://agora.ta-amps.workers.dev/status/", "https://agora.ta-amps.workers.dev/decks/public-good-marketplace/#status", "https://agora.ta-amps.workers.dev/decks/server-workers/#status", "https://home.ta-amps.workers.dev", "https://agora.ta-amps.workers.dev", "https://eranos.ta-amps.workers.dev/nonprofits", "https://eranos.ta-amps.workers.dev/requests", "https://eranos.ta-amps.workers.dev/connect", "https://tessera.ta-amps.workers.dev", "https://eranos.ta-amps.workers.dev/", "https://herma.ta-amps.workers.dev", "https://home.ta-amps.workers.dev/connect", "https://tessera.ta-amps.workers.dev/connect", "https://tessera.ta-amps.workers.dev/mcp`", "https://tessera.ta-amps.workers.dev/connect.json`", "https://tessera.ta-amps.workers.dev/v1/openapi.json`", "https://tessera.ta-amps.workers.dev/.well-known/agent-card.json`", "https://herma.ta-amps.workers.dev/dashboard", "https://agora.ta-amps.workers.dev/studio/", "https://agora.ta-amps.workers.dev/deploy/", "https://agora.ta-amps.workers.dev/film/" ], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 3.0, "score_meta_tooling": 2.3, "score_tech_depth": 2.0, "score_demo": 2.5, "score_total": 9.8, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "High-impact domain", "+0.4" ], [ "Eval & benchmark proof", "+0.3" ], [ "Docker packaging", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ], [ "Open-weights / fine-tuning", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (551)", "+0.6" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Agent / eval harness", "+0.2" ], [ "Automated CI workflow", "+0.2" ], [ "PR review workflow (136 PRs)", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Video walkthrough", "+1.1" ], [ "Reproducible setup guide", "+0.4" ], [ "Live web deployment", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 2, "is_new": true, "commits_delta": 551, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "alsopgroup/lanemint-meta-hackathon", "html_url": "https://github.com/alsopgroup/lanemint-meta-hackathon", "track": "Push the Frontier", "domain": "Finance, Crypto & Web3", "summary": "Deterministic benchmark testing Muse on messy quant market-data cleaning", "readme_summary": "Procedurally generates messy CSVs with hidden data problems to test Muse models on exact numeric cleaning. Python + Docker benchmark with deterministic scorer. Finds Muse Spark 1.3 solves 70% on tools_frontier tier.", "tech_highlights": [ "Muse Spark 1.3", "Python Benchmark", "Deterministic Scorer" ], "created_at": "2026-10-26T04:30:26Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 112, "commits_before_window": 0, "prs_total": 34, "prs_merged": 34, "is_preexisting": false, "has_docker": true, "has_tests": true, "has_src": true, "has_ci": true, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": true, "has_eval_benchmarks": true, "has_setup_guide": true, "has_video_demo": true, "video_urls": [ "https://youtu.be/r-mvSwYUFLc" ], "has_live_deploy": true, "live_urls": [ "https://lanemint.com" ], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 1, "score_impact": 2.9, "score_meta_tooling": 2.3, "score_tech_depth": 2.0, "score_demo": 2.5, "score_total": 9.7, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "Domain alignment", "+0.3" ], [ "Eval & benchmark proof", "+0.3" ], [ "Docker packaging", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ], [ "Open-weights / fine-tuning", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (112)", "+0.6" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Agent / eval harness", "+0.2" ], [ "Automated CI workflow", "+0.2" ], [ "PR review workflow (34 PRs)", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Video walkthrough", "+1.1" ], [ "Reproducible setup guide", "+0.4" ], [ "Live web deployment", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 3, "is_new": false, "commits_delta": 20, "rank_delta": 7, "commits_delta_last_run": 1 }, { "full_name": "QuintinBotes/stint", "html_url": "https://github.com/QuintinBotes/stint", "track": "Push the Frontier", "domain": "Developer Tooling, Infra & Security", "summary": "Local-first control plane making tasks persist across coding agent sessions", "readme_summary": "Makes the task, not chat, the unit of work for coding agents using repo folders and git worktrees. Runs tests, writes continuation packets, local model review. Runs on-machine using Meta Muse models by default.", "tech_highlights": [ "Muse Models", "Git Worktrees", "Local-First Tasks" ], "created_at": "2026-10-26T14:46:18Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 372, "commits_before_window": 0, "prs_total": 11, "prs_merged": 3, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": true, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": true, "has_eval_benchmarks": true, "has_setup_guide": true, "has_video_demo": true, "video_urls": [ "https://youtu.be/ejYyHgkVOWg" ], "has_live_deploy": true, "live_urls": [ "https://quintinbotes.github.io/stint/demo/", "https://quintinbotes.github.io/stint/" ], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.6, "score_meta_tooling": 2.3, "score_tech_depth": 2.0, "score_demo": 2.5, "score_total": 9.4, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "High-impact domain", "+0.4" ], [ "Eval & benchmark proof", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ], [ "Open-weights / fine-tuning", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (372)", "+0.6" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Agent / eval harness", "+0.2" ], [ "Automated CI workflow", "+0.2" ], [ "PR review workflow (3 PRs)", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Video walkthrough", "+1.1" ], [ "Reproducible setup guide", "+0.4" ], [ "Live web deployment", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 4, "is_new": false, "commits_delta": 141, "rank_delta": 31, "commits_delta_last_run": 0 }, { "full_name": "matrixagentsocial/matrix-globe", "html_url": "https://github.com/matrixagentsocial/matrix-globe", "track": "Push the Frontier", "domain": "Developer Tooling, Infra & Security", "summary": "Code reviewer that must prove bugs with failing sandbox tests", "readme_summary": "Review loop where reviewer can only report defects with reproducing failing tests in isolated sandbox. Builder revises until pass, sealed in SHA-256 certificate verifiable in browser. Muse-powered with 902 proof bundles.", "tech_highlights": [ "Muse Reviewer", "Sandbox Testing", "SHA-256 Proofs" ], "created_at": "2026-10-26T21:12:31Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 62, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": true, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": true, "has_eval_benchmarks": true, "has_setup_guide": true, "has_video_demo": true, "video_urls": [ "https://matrixagentsocial.github.io/matrix-globe/matrix-globe-demo.mp4" ], "has_live_deploy": true, "live_urls": [ "https://matrixagentsocial.github.io/matrix-globe/", "https://matrixagentsocial.github.io/matrix-globe/matrix-globe-demo.mp4" ], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.6, "score_meta_tooling": 2.3, "score_tech_depth": 1.9, "score_demo": 2.5, "score_total": 9.3, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "High-impact domain", "+0.4" ], [ "Eval & benchmark proof", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ], [ "Open-weights / fine-tuning", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (62)", "+0.6" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Agent / eval harness", "+0.2" ], [ "Automated CI workflow", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Video walkthrough", "+1.1" ], [ "Reproducible setup guide", "+0.4" ], [ "Live web deployment", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 5, "is_new": false, "commits_delta": 15, "rank_delta": 363, "commits_delta_last_run": 0 }, { "full_name": "0xNoramiya/ventriloquist", "html_url": "https://github.com/0xNoramiya/ventriloquist", "track": "Build for Your World", "domain": "Healthcare, Civic Tech & Sustainability", "summary": "Bedside voice aid letting ventilated ICU patients answer yes/no with gestures", "readme_summary": "Phone on bed rail asks most-informative yes/no questions and reads eyebrow, blink or finger movement, speaking only confirmed messages. Full-stack app with camera pipeline and evals. Uses Muse Spark for dialogue and SAM 3.1 for movement.", "tech_highlights": [ "Muse Spark", "SAM 3.1 Vision", "Fly.io + Docker" ], "created_at": "2026-10-27T00:26:02Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 102, "commits_before_window": 0, "prs_total": 11, "prs_merged": 10, "is_preexisting": false, "has_docker": true, "has_tests": false, "has_src": true, "has_ci": true, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": true, "has_eval_benchmarks": true, "has_setup_guide": true, "has_video_demo": true, "video_urls": [ "https://github.com/0xNoramiya/ventriloquist/releases/download/v0.2.0/ventriloquist-demo.mp4" ], "has_live_deploy": true, "live_urls": [ "https://ventriloquist.fly.dev" ], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.6, "score_meta_tooling": 2.3, "score_tech_depth": 1.8, "score_demo": 2.5, "score_total": 9.2, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "High-impact domain", "+0.4" ], [ "Eval & benchmark proof", "+0.3" ], [ "Docker packaging", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ], [ "Open-weights / fine-tuning", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (102)", "+0.6" ], [ "Modular src/ architecture", "+0.3" ], [ "Agent / eval harness", "+0.2" ], [ "Automated CI workflow", "+0.2" ], [ "PR review workflow (10 PRs)", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Video walkthrough", "+1.1" ], [ "Reproducible setup guide", "+0.4" ], [ "Live web deployment", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 6, "is_new": true, "commits_delta": 102, "rank_delta": 0, "commits_delta_last_run": 2 }, { "full_name": "quanticsoul4772/glint", "html_url": "https://github.com/quanticsoul4772/glint", "track": "Push the Frontier", "domain": "Developer Tooling, Infra & Security", "summary": "Policy gates that block unsafe bank agent writes before they run", "readme_summary": "Verifiable banking agents using Muse Glimmer 30B with deterministic policy gates. Each write is checked against coded bank policy and live records; denied writes are blocked with reasons and all decisions go to a hash-chained log.", "tech_highlights": [ "Muse Glimmer 30B", "Policy Gates", "Hash-chained Log" ], "created_at": "2026-10-31T21:36:51Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 457, "commits_before_window": 0, "prs_total": 15, "prs_merged": 15, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": true, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": true, "has_eval_benchmarks": true, "has_setup_guide": true, "has_video_demo": true, "video_urls": [ "https://youtu.be/tdQuhfSO_9w" ], "has_live_deploy": true, "live_urls": [ "https://quanticsoul4772.github.io/glint/" ], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.6, "score_meta_tooling": 2.0, "score_tech_depth": 2.0, "score_demo": 2.5, "score_total": 9.1, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "High-impact domain", "+0.4" ], [ "Eval & benchmark proof", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ], [ "Open-weights / fine-tuning", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (457)", "+0.6" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Agent / eval harness", "+0.2" ], [ "Automated CI workflow", "+0.2" ], [ "PR review workflow (15 PRs)", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Video walkthrough", "+1.1" ], [ "Reproducible setup guide", "+0.4" ], [ "Live web deployment", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 7, "is_new": true, "commits_delta": 457, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "halo-sw/ithaca", "html_url": "https://github.com/halo-sw/ithaca", "track": "Build for Your World", "domain": "General & Emerging Applications", "summary": "Simulates 30 days of living in two homes to compare commute, cost and safety", "readme_summary": "Pre-living agent where AI household lives in candidate homes before signing. Docker pipeline with briefs and docs. Uses Muse Spark 1.3 for day-by-day commute, money and walk-home analysis.", "tech_highlights": [ "Muse Spark 1.3", "Docker Pipeline", "Home Simulation" ], "created_at": "2026-10-28T15:29:15Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 591, "commits_before_window": 0, "prs_total": 22, "prs_merged": 21, "is_preexisting": false, "has_docker": true, "has_tests": true, "has_src": false, "has_ci": true, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": true, "has_eval_benchmarks": true, "has_setup_guide": true, "has_video_demo": true, "video_urls": [ "https://github.com/halo-sw/ithaca/releases/download/demo-video/ithaca-demo.mp4" ], "has_live_deploy": true, "live_urls": [ "https://halo-sw.github.io/ithaca/", "https://halo-sw.github.io/ithaca/?replay=menlo-month&lang=en", "https://halo-sw.github.io/ithaca/?replay=seoul-couple&lang=ko", "https://halo-sw.github.io/ithaca/?lang=ko", "https://halo-sw.github.io/ithaca/?chat=%ED%8C%90%EA%B5%90%EB%A1%9C+%EC%B6%9C%EA%B7%BC%ED%95%98%EB%8A%94+%EC%8B%A0%EC%9E%85%2C+%EC%97%B0%EB%B4%89+4%EC%B2%9C%2C+%EB%AA%A8%EC%9D%80+%EB%8F%88+5%EC%B2%9C%2C+%EC%A0%84%EC%84%B8+2%EC%96%B5+%EC%9D%B4%ED%95%98&lang=ko", "https://halo-sw.github.io/ithaca/?chat=I+work+at+Meta+HQ+in+Menlo+Park.+Two+of+us%2C+rent+up+to+%244%2C500+a+month.&lang=en", "https://halo-sw.github.io/ithaca/?chat=&listing=1&lang=en", "https://halo-sw.github.io/ithaca/?mode=sim&scenario=demo-two-homes&tour=demo" ], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.4, "score_meta_tooling": 2.3, "score_tech_depth": 1.8, "score_demo": 2.5, "score_total": 9.0, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "General domain", "+0.2" ], [ "Eval & benchmark proof", "+0.3" ], [ "Docker packaging", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ], [ "Open-weights / fine-tuning", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (591)", "+0.6" ], [ "Automated test suite", "+0.3" ], [ "Agent / eval harness", "+0.2" ], [ "Automated CI workflow", "+0.2" ], [ "PR review workflow (21 PRs)", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Video walkthrough", "+1.1" ], [ "Reproducible setup guide", "+0.4" ], [ "Live web deployment", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 8, "is_new": true, "commits_delta": 591, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "thecodekaizen/veil", "html_url": "https://github.com/thecodekaizen/veil", "track": "Push the Frontier", "domain": "Developer Tooling, Infra & Security", "summary": "Scans your video for faces, plates and spoken IDs then redacts before posting", "readme_summary": "Muse Spark proposes identifiers, SAM 3.1 tracks them, Muse Voice detects spoken numbers; deterministic code redacts and re-checks export. Python pipeline with 122 tests and local Glimmer 30B option.", "tech_highlights": [ "Muse Spark", "SAM 3.1 Tracking", "Muse Voice" ], "created_at": "2026-11-01T06:26:35Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 203, "commits_before_window": 2, "prs_total": 1, "prs_merged": 0, "is_preexisting": true, "has_docker": false, "has_tests": false, "has_src": true, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": true, "has_eval_benchmarks": true, "has_setup_guide": true, "has_video_demo": true, "video_urls": [ "https://thecodekaizen.github.io/veil/video/veil-demo.mp4" ], "has_live_deploy": true, "live_urls": [ "https://thecodekaizen.github.io/veil/", "https://thecodekaizen.github.io/veil/video/veil-demo.mp4", "https://thecodekaizen.github.io/veil/#/desk?run=c2", "https://thecodekaizen.github.io/veil/#results" ], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 1, "score_impact": 2.6, "score_meta_tooling": 2.3, "score_tech_depth": 1.4, "score_demo": 2.5, "score_total": 8.8, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "High-impact domain", "+0.4" ], [ "Eval & benchmark proof", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ], [ "Open-weights / fine-tuning", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (203)", "+0.6" ], [ "Modular src/ architecture", "+0.3" ], [ "Agent / eval harness", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Video walkthrough", "+1.1" ], [ "Reproducible setup guide", "+0.4" ], [ "Live web deployment", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 9, "is_new": true, "commits_delta": 203, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "samoxis/blinkflow", "html_url": "https://github.com/samoxis/blinkflow", "track": "Push the Frontier", "domain": "Robotics, IoT & Manufacturing", "summary": "Voice-to-fix loop that patches robot behavior and proves it in twin", "readme_summary": "BlinkFlow turns spoken incident reports into simulator fixes with replay proof. Includes Python twin, sidecar, Muse-gate and example purple-box run. Provides static reports, tests and judge-path CI.", "tech_highlights": [ "Python Simulator", "Muse-Gate", "Replay Verification" ], "created_at": "2026-10-26T17:00:58Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 153, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": true, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": true, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": true, "video_urls": [ "https://youtu.be/6EDwRU-f-xI" ], "has_live_deploy": true, "live_urls": [ "https://samoxis.github.io/blinkflow/report/" ], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.3, "score_meta_tooling": 2.3, "score_tech_depth": 1.7, "score_demo": 2.5, "score_total": 8.8, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "High-impact domain", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ], [ "Open-weights / fine-tuning", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (153)", "+0.6" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Automated CI workflow", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Video walkthrough", "+1.1" ], [ "Reproducible setup guide", "+0.4" ], [ "Live web deployment", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 10, "is_new": true, "commits_delta": 153, "rank_delta": 0, "commits_delta_last_run": 6 }, { "full_name": "bgaravelos/montivo", "html_url": "https://github.com/bgaravelos/montivo", "track": "Build for Your World", "domain": "Gaming, Entertainment & Creative Media", "summary": "Agent video editor that cuts spoken footage then watches and re-cuts its edit", "readme_summary": "Takes spoken footage and a brief to select lines and cut on word boundaries. Renders, reviews its own cut with vision scoring, then re-cuts iteratively. Built on Meta Muse Spark, Muse Voice and SAM 3.1.", "tech_highlights": [ "Muse Spark", "SAM 3.1 Vision", "Muse Voice" ], "created_at": "2026-10-26T17:12:30Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 359, "commits_before_window": 0, "prs_total": 4, "prs_merged": 4, "is_preexisting": false, "has_docker": true, "has_tests": true, "has_src": true, "has_ci": true, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": true, "has_setup_guide": true, "has_video_demo": true, "video_urls": [ "https://www.youtube.com/watch?v=JRa-nPJJVEc" ], "has_live_deploy": true, "live_urls": [ "https://bgaravelos--montivo-web.us-east.modal.run/s/CAlQGWBgIBbo" ], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 2, "score_impact": 2.4, "score_meta_tooling": 1.8, "score_tech_depth": 2.0, "score_demo": 2.5, "score_total": 8.7, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "General domain", "+0.2" ], [ "Eval & benchmark proof", "+0.3" ], [ "Docker packaging", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (359)", "+0.6" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Agent / eval harness", "+0.2" ], [ "Automated CI workflow", "+0.2" ], [ "PR review workflow (4 PRs)", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Video walkthrough", "+1.1" ], [ "Reproducible setup guide", "+0.4" ], [ "Live web deployment", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 11, "is_new": false, "commits_delta": 174, "rank_delta": 46, "commits_delta_last_run": 0 }, { "full_name": "tamzid2001/frontiersight-ai", "html_url": "https://github.com/tamzid2001/frontiersight-ai", "track": "Push the Frontier", "domain": "Multimodal Vision & Video (SAM / Vision)", "summary": "Turns video into verifiable physical-world safety intelligence", "readme_summary": "Converts video into measured physical-world events with verifiable evidence instead of vague captions. Python pipeline with edge Docker, coverage and evaluation. Uses Meta vision models including SAM-style segmentation for forklift safety.", "tech_highlights": [ "SAM Vision", "Video Intelligence", "Python + Docker" ], "created_at": "2026-10-27T17:40:50Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 92, "commits_before_window": 0, "prs_total": 5, "prs_merged": 5, "is_preexisting": false, "has_docker": true, "has_tests": true, "has_src": true, "has_ci": true, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": true, "video_urls": [ "https://youtu.be/mYTkPqigoz8" ], "has_live_deploy": true, "live_urls": [ "https://frontiersight-ai.vercel.app", "https://frontiersight-ai.vercel.app/physical-intelligence", "https://frontiersight-ai.vercel.app/api-guide.html", "https://frontiersight-ai.vercel.app/openapi.json" ], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.6, "score_meta_tooling": 1.6, "score_tech_depth": 1.9, "score_demo": 2.5, "score_total": 8.6, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "Domain alignment", "+0.3" ], [ "Docker packaging", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (92)", "+0.6" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Automated CI workflow", "+0.2" ], [ "PR review workflow (5 PRs)", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Video walkthrough", "+1.1" ], [ "Reproducible setup guide", "+0.4" ], [ "Live web deployment", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 12, "is_new": false, "commits_delta": 25, "rank_delta": -11, "commits_delta_last_run": 0 }, { "full_name": "ziffan/LexRAGLab-Meta2026Hackathon", "html_url": "https://github.com/ziffan/LexRAGLab-Meta2026Hackathon", "track": "Push the Frontier", "domain": "Legal & Compliance", "summary": "Lab to measure chunking and retrieval for Indonesian legal RAG", "readme_summary": "LexRAGLab benchmarks chunking and retrieval settings on Indonesian legal clauses. Python backend with frontend and measured eval harness. Uses Muse models to feed LLMs the right clauses.", "tech_highlights": [ "Muse Models", "RAG Eval Harness", "Python Backend" ], "created_at": "2026-10-26T16:22:56Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 449, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": true, "has_ci": true, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": true, "has_eval_benchmarks": true, "has_setup_guide": true, "has_video_demo": true, "video_urls": [ "https://youtu.be/BMXQfIeGhqw", "https://www.youtube.com/watch?v=BMXQfIeGhqw" ], "has_live_deploy": true, "live_urls": [ "https://ziffan.github.io/LexRAGLab-Meta2026Hackathon/" ], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 1, "score_impact": 2.5, "score_meta_tooling": 1.8, "score_tech_depth": 1.6, "score_demo": 2.5, "score_total": 8.4, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "Domain alignment", "+0.3" ], [ "Eval & benchmark proof", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "Open-weights / fine-tuning", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (449)", "+0.6" ], [ "Modular src/ architecture", "+0.3" ], [ "Agent / eval harness", "+0.2" ], [ "Automated CI workflow", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Video walkthrough", "+1.1" ], [ "Reproducible setup guide", "+0.4" ], [ "Live web deployment", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 13, "is_new": true, "commits_delta": 449, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "ConWan30/qortime-ai", "html_url": "https://github.com/ConWan30/qortime-ai", "track": "Push the Frontier", "domain": "Gaming, Entertainment & Creative Media", "summary": "Explains and stress-tests game referee results without ever deciding outcomes", "readme_summary": "Verifiable referee produces signed receipts for matches while Meta models only explain, attack and visualize results. Uses Muse Spark for explanation, Muse Wonder for adversarial test and SAM 3.1 for vision. Python pipeline plus web verifier.", "tech_highlights": [ "Muse Spark Explain", "Muse Wonder Attack", "SAM 3.1 Vision" ], "created_at": "2026-10-27T21:51:47Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 29, "commits_before_window": 0, "prs_total": 29, "prs_merged": 28, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": true, "has_setup_guide": true, "has_video_demo": true, "video_urls": [ "https://youtu.be/vlGJ1LXxumE" ], "has_live_deploy": true, "live_urls": [ "https://qortime.com", "https://qortime-referee-production.up.railway.app/v1/log/inclusion/8a3a6d60e498c607fef79e013afab333b760fb7c9e58e16fa9912683c98cb71b`", "https://agent-api-production-0e55.up.railway.app/agent/v1/verify?url=https://qortime.com/matches/220105/", "https://agent-api-production-0e55.up.railway.app/agent/v1/openapi.json" ], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.4, "score_meta_tooling": 1.8, "score_tech_depth": 1.7, "score_demo": 2.5, "score_total": 8.4, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "General domain", "+0.2" ], [ "Eval & benchmark proof", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (29)", "+0.4" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Agent / eval harness", "+0.2" ], [ "PR review workflow (28 PRs)", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Video walkthrough", "+1.1" ], [ "Reproducible setup guide", "+0.4" ], [ "Live web deployment", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 14, "is_new": false, "commits_delta": 0, "rank_delta": -9, "commits_delta_last_run": 0 }, { "full_name": "rockeykotwal/backend-friend", "html_url": "https://github.com/rockeykotwal/backend-friend", "track": "Push the Frontier", "domain": "Developer Tooling, Infra & Security", "summary": "Detects N+1, missing indexes and slow DB queries with AI fixes", "readme_summary": "AI-powered database analyzer that finds N+1 queries, missing indexes, overfetching and slow queries across backend languages. Returns fixed code. Built with Meta AI, Node.js backend and web UI.", "tech_highlights": [ "Meta AI", "Node.js + Analyzer", "Next.js UI" ], "created_at": "2026-10-26T18:13:16Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 112, "commits_before_window": 0, "prs_total": 42, "prs_merged": 42, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": true, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": true, "video_urls": [ "https://youtu.be/03KrFQC5bB8" ], "has_live_deploy": true, "live_urls": [ "https://backend-friend.rockeykotwal.in/" ], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 4, "score_impact": 2.3, "score_meta_tooling": 1.6, "score_tech_depth": 1.9, "score_demo": 2.5, "score_total": 8.3, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "High-impact domain", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (112)", "+0.6" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Automated CI workflow", "+0.2" ], [ "PR review workflow (42 PRs)", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Video walkthrough", "+1.1" ], [ "Reproducible setup guide", "+0.4" ], [ "Live web deployment", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 15, "is_new": true, "commits_delta": 112, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "prohle/schedulesolve-ai", "html_url": "https://github.com/prohle/schedulesolve-ai", "track": "Build for Your World", "domain": "Autonomous Agents & Workflow Automation", "summary": "Agentic university timetabler where AI proposes constraints and solvers verify them.", "readme_summary": "ScheduleSolve AI builds conflict-free university timetables via agentic constraint proposal and CP-SAT verification. Stack is Python FastAPI backend, Next.js 16 frontend, Docker Compose, and native C++ solver. Uses Muse Spark for reasoning and Meta Voice/Spark Open at runtime.", "tech_highlights": [ "Muse Spark", "CP-SAT + C++ Solver", "Next.js + FastAPI" ], "created_at": "2026-10-27T12:45:48Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 105, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": true, "has_tests": true, "has_src": true, "has_ci": true, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": true, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": true, "video_urls": [ "https://github.com/prohle/schedulesolve-ai/releases/download/demo-video/final.mp4" ], "has_live_deploy": true, "live_urls": [ "https://prohle--schedulesolve-ai-ui-web.us-east.modal.run", "https://prohle--schedulesolve-ai-api.us-east.modal.run" ], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.3, "score_meta_tooling": 1.8, "score_tech_depth": 1.7, "score_demo": 2.5, "score_total": 8.3, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "High-impact domain", "+0.4" ], [ "Docker packaging", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "Open-weights / fine-tuning", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (105)", "+0.6" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Automated CI workflow", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Video walkthrough", "+1.1" ], [ "Reproducible setup guide", "+0.4" ], [ "Live web deployment", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 16, "is_new": true, "commits_delta": 105, "rank_delta": 0, "commits_delta_last_run": 6 }, { "full_name": "Unclefole/yebo-muse-agent", "html_url": "https://github.com/Unclefole/yebo-muse-agent", "track": "Build for Your World", "domain": "Finance, Crypto & Web3", "summary": "Muse reads invoices and Yebo enforces human-approved payment limits", "readme_summary": "Muse Spark 1.3 reads invoice images/PDFs to schema-checked JSON and plans payments with tool calls. Yebo checks every payment against approved limits so tricked AI cannot mis-pay. Node.js demo with Railway hosting and dry-run replays.", "tech_highlights": [ "Muse Spark 1.3", "Vision Invoice Parse", "Yebo Policy Guard" ], "created_at": "2026-10-26T16:00:37Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 82, "commits_before_window": 0, "prs_total": 37, "prs_merged": 37, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": true, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": true, "video_urls": [ "https://youtu.be/QfSVHJDowAU" ], "has_live_deploy": true, "live_urls": [ "https://yebo-muse-demo-production.up.railway.app" ], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.8, "score_meta_tooling": 2.3, "score_tech_depth": 1.7, "score_demo": 2.5, "score_total": 8.3, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ], [ "Open-weights / fine-tuning", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (82)", "+0.6" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "PR review workflow (37 PRs)", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Video walkthrough", "+1.1" ], [ "Reproducible setup guide", "+0.4" ], [ "Live web deployment", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 17, "is_new": false, "commits_delta": 14, "rank_delta": 66, "commits_delta_last_run": 0 }, { "full_name": "denmarkamanodaya/meta-hackathon-nimbytes", "html_url": "https://github.com/denmarkamanodaya/meta-hackathon-nimbytes", "track": "Build for Your World", "domain": "Multimodal Vision & Video (SAM / Vision)", "summary": "Zero-byte cloud filesystem that plays local and searches video like text", "readme_summary": "nimbytes stores family video library in cloud with zero bytes on device while playing like local. Meta models understand clips for text search plus iGuide and iRead accessibility. Go API, desktop client, Docker and Caddy.", "tech_highlights": [ "Meta AI Video Search", "Zero-Byte Filesystem", "Go + Docker" ], "created_at": "2026-10-26T17:05:29Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 485, "commits_before_window": 0, "prs_total": 14, "prs_merged": 10, "is_preexisting": false, "has_docker": true, "has_tests": true, "has_src": true, "has_ci": true, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": true, "video_urls": [ "https://youtu.be/U1ZFNs1BktY" ], "has_live_deploy": true, "live_urls": [ "https://3-104-132-162.sslip.io" ], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.2, "score_meta_tooling": 1.6, "score_tech_depth": 1.9, "score_demo": 2.5, "score_total": 8.2, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Docker packaging", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (485)", "+0.6" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Automated CI workflow", "+0.2" ], [ "PR review workflow (10 PRs)", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Video walkthrough", "+1.1" ], [ "Reproducible setup guide", "+0.4" ], [ "Live web deployment", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 18, "is_new": true, "commits_delta": 485, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "edward321416-maker/fieldless", "html_url": "https://github.com/edward321416-maker/fieldless", "track": "Build for Your World", "domain": "Healthcare, Civic Tech & Sustainability", "summary": "Surveys street assets and sidewalk conditions from Mapillary photos to cut fieldwork", "readme_summary": "Picks an area and records assets, curb ramps, steps and blockages with evidence photos from Mapillary imagery. Uses SAM 3.1 for segmentation, Muse Spark to generate new survey types, Glimmer and Modal for large runs.", "tech_highlights": [ "SAM 3.1 Vision", "Muse Spark", "Mapillary + Modal" ], "created_at": "2026-10-26T17:41:45Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 333, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": true, "has_tests": true, "has_src": true, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": true, "has_eval_benchmarks": true, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": true, "live_urls": [ "https://edward321416--fieldless-web.us-east.modal.run", "https://edward321416--fieldless-web.us-east.modal.run/#scan=17&item=4" ], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 1, "score_impact": 2.6, "score_meta_tooling": 2.5, "score_tech_depth": 1.7, "score_demo": 1.4, "score_total": 8.2, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "High-impact domain", "+0.4" ], [ "Eval & benchmark proof", "+0.3" ], [ "Docker packaging", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ], [ "Open-weights / fine-tuning", "+0.5" ], [ "Published HF Hub weights", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (333)", "+0.6" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Agent / eval harness", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Live web deployment", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 19, "is_new": false, "commits_delta": 75, "rank_delta": -15, "commits_delta_last_run": 0 }, { "full_name": "StefanRohringer/muse-qc-cell", "html_url": "https://github.com/StefanRohringer/muse-qc-cell", "track": "Push the Frontier", "domain": "Robotics, IoT & Manufacturing", "summary": "Robot arm cell where Muse Spark inspects and sorts molded parts live", "readme_summary": "A reBot Arm B601-DM picks parts while a Muse Spark agent controls inspection and sorting. SAM 3.1 counts levers in close-ups to route good or bad boxes. Uses real hardware with calibration and eval tooling.", "tech_highlights": [ "Muse Spark Agent", "SAM 3.1 Vision", "reBot Arm Hardware" ], "created_at": "2026-10-26T20:25:34Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 154, "commits_before_window": 0, "prs_total": 7, "prs_merged": 7, "is_preexisting": false, "has_docker": true, "has_tests": true, "has_src": true, "has_ci": true, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": true, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": true, "live_urls": [ "https://stefanrohringer.github.io/muse-qc-cell/" ], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 3.0, "score_meta_tooling": 1.8, "score_tech_depth": 2.0, "score_demo": 1.4, "score_total": 8.2, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "High-impact domain", "+0.4" ], [ "Eval & benchmark proof", "+0.3" ], [ "Docker packaging", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (154)", "+0.6" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Agent / eval harness", "+0.2" ], [ "Automated CI workflow", "+0.2" ], [ "PR review workflow (7 PRs)", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Live web deployment", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 20, "is_new": false, "commits_delta": 86, "rank_delta": 41, "commits_delta_last_run": 6 }, { "full_name": "IgnacioSearles/oqed", "html_url": "https://github.com/IgnacioSearles/oqed", "track": "Push the Frontier", "domain": "Developer Tooling, Infra & Security", "summary": "LLM superoptimizer that beats clang -O3 on hot x86-64 functions", "readme_summary": "Finds hot C/C++ functions, asks Muse for faster assembly, verifies correctness and keeps wins via CC=oqed-cc. Harness with benchmarks, sweeps and web UI. Uses Meta Muse models for assembly generation.", "tech_highlights": [ "Muse Models", "Clang + GCC -O3", "x86-64 Superopt" ], "created_at": "2026-10-26T12:22:41Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 105, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": true, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": true, "has_eval_benchmarks": true, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": true, "live_urls": [ "https://ignaciosearles.github.io/oqed/" ], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 1, "score_impact": 2.6, "score_meta_tooling": 2.3, "score_tech_depth": 1.9, "score_demo": 1.4, "score_total": 8.2, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "High-impact domain", "+0.4" ], [ "Eval & benchmark proof", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ], [ "Open-weights / fine-tuning", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (105)", "+0.6" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Agent / eval harness", "+0.2" ], [ "Automated CI workflow", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Live web deployment", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 21, "is_new": true, "commits_delta": 105, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "agmonp/muse-life-graph", "html_url": "https://github.com/agmonp/muse-life-graph", "track": "Build for Your World", "domain": "Gaming, Entertainment & Creative Media", "summary": "Turns thousands of family photos into a searchable graph and AI film.", "readme_summary": "Muse Life Graph ingests family libraries into a reasoned life graph for search and Q&A, then a crew of Muse agents writes, cuts and critiques a personal film. Python + Modal with Windows app.", "tech_highlights": [ "Muse Agents", "Life Graph DB", "Modal + Python" ], "created_at": "2026-10-26T09:28:32Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 59, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": true, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": true, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": true, "video_urls": [ "https://youtu.be/JX4o7B06awk", "https://www.youtube.com/watch?v=JX4o7B06awk" ], "has_live_deploy": true, "live_urls": [ "https://agmonporat--muse-life-graph-web.us-east.modal.run" ], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.7, "score_meta_tooling": 2.3, "score_tech_depth": 1.7, "score_demo": 2.5, "score_total": 8.2, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "General domain", "+0.2" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ], [ "Open-weights / fine-tuning", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (59)", "+0.6" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Automated CI workflow", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Video walkthrough", "+1.1" ], [ "Reproducible setup guide", "+0.4" ], [ "Live web deployment", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 22, "is_new": false, "commits_delta": 41, "rank_delta": 300, "commits_delta_last_run": 0 }, { "full_name": "sushant-me/only-you", "html_url": "https://github.com/sushant-me/only-you", "track": "Push the Frontier", "domain": "Developer Tooling, Infra & Security", "summary": "Provenance gate that decides which voices a wearable agent must obey.", "readme_summary": "Authority layer for glasses agents that filters audio commands by speaker provenance. Uses Muse Spark for reasoning, Muse Wonder for scene reading, Muse Voice Transcribe and SAM 3.1 grounding. Includes playground demo and audit docs.", "tech_highlights": [ "Muse Spark", "Muse Wonder", "SAM 3.1 Grounding" ], "created_at": "2026-10-28T07:23:27Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 269, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": true, "has_tests": true, "has_src": true, "has_ci": true, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": true, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": true, "live_urls": [ "https://sushant-me.github.io/only-you/playground.html", "https://sushant-me.github.io/only-you/", "https://sushant-me.github.io/only-you/verify.html" ], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.7, "score_meta_tooling": 2.3, "score_tech_depth": 1.7, "score_demo": 1.4, "score_total": 8.1, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "High-impact domain", "+0.4" ], [ "Docker packaging", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ], [ "Open-weights / fine-tuning", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (269)", "+0.6" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Automated CI workflow", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Live web deployment", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 23, "is_new": false, "commits_delta": 10, "rank_delta": -17, "commits_delta_last_run": 0 }, { "full_name": "athos-agent/athos", "html_url": "https://github.com/athos-agent/athos", "track": "Push the Frontier", "domain": "Developer Tooling, Infra & Security", "summary": "Portable local memory that lets any agent reuse your checklists and working rules", "readme_summary": "Saves ways of working as portable markdown memory and loads it for matching requests across agents. Plugin adapters for Claude Code and Codex; uses Muse models for matching and recall.", "tech_highlights": [ "Agent Memory", "Claude + Codex Plugin", "Local Markdown Store" ], "created_at": "2026-10-25T19:42:09Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 229, "commits_before_window": 21, "prs_total": 101, "prs_merged": 100, "is_preexisting": true, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": true, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": true, "has_eval_benchmarks": false, "has_setup_guide": false, "has_video_demo": true, "video_urls": [ "https://youtu.be/4JabA-KajK0", "https://www.youtube.com/watch?v=eRrc1pUY5oU" ], "has_live_deploy": true, "live_urls": [ "https://athos-agent.github.io/athos/" ], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 5, "score_impact": 2.3, "score_meta_tooling": 1.8, "score_tech_depth": 1.9, "score_demo": 2.1, "score_total": 8.1, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "High-impact domain", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ], [ "Open-weights / fine-tuning", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (229)", "+0.6" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Automated CI workflow", "+0.2" ], [ "PR review workflow (100 PRs)", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Video walkthrough", "+1.1" ], [ "Live web deployment", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 24, "is_new": true, "commits_delta": 229, "rank_delta": 0, "commits_delta_last_run": 2 }, { "full_name": "antonmareo10/conforme", "html_url": "https://github.com/antonmareo10/conforme", "track": "Build for Your World", "domain": "Business, Sales & Commerce", "summary": "Photos supplier delivery notes, double-checks totals and flags overcharges", "readme_summary": "Separates delivery notes from one photo, reads money numbers twice in code. Agent zooms to re-read, checks price history and cites evidence. Built with Next.js, voice Q&A and swappable Meta open-weight model.", "tech_highlights": [ "Muse Spark Vision", "Next.js + Vercel", "Voice Q&A" ], "created_at": "2026-10-26T20:25:50Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 55, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": true, "has_ci": true, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": true, "has_eval_benchmarks": true, "has_setup_guide": false, "has_video_demo": true, "video_urls": [ "https://youtu.be/_ev_sB6WhY0" ], "has_live_deploy": true, "live_urls": [ "https://conforme-mu.vercel.app", "https://conforme-mu.vercel.app/sesion?muestra=encimera&modelo=abierto" ], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.1, "score_meta_tooling": 2.3, "score_tech_depth": 1.6, "score_demo": 2.1, "score_total": 8.1, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Eval & benchmark proof", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ], [ "Open-weights / fine-tuning", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (55)", "+0.6" ], [ "Modular src/ architecture", "+0.3" ], [ "Agent / eval harness", "+0.2" ], [ "Automated CI workflow", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Video walkthrough", "+1.1" ], [ "Live web deployment", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 25, "is_new": false, "commits_delta": 9, "rank_delta": -2, "commits_delta_last_run": 0 }, { "full_name": "dl88jing/seefix", "html_url": "https://github.com/dl88jing/seefix", "track": "Build for Your World", "domain": "Multimodal Vision & Video (SAM / Vision)", "summary": "Camera-first repair copilot that identifies parts and verifies each fix step.", "readme_summary": "Next.js app where users photograph a fixture to get model ID, overlaid next steps and safety checks. Uses Muse Spark Open via Baseten for visual identification on /lab, Modal backend, narrated Playwright demo.", "tech_highlights": [ "Muse Spark Open", "Next.js + Modal", "Baseten Inference" ], "created_at": "2026-10-26T16:06:39Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 15, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": true, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": true, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": true, "video_urls": [ "https://youtu.be/Mk7XkNJ0lXE", "https://github.com/dl88jing/seefix/releases/download/v0.2.0/seefix-demo-v2.mp4" ], "has_live_deploy": true, "live_urls": [ "https://seefix.vercel.app", "https://seefix.vercel.app/lab", "https://seefix.vercel.app/api/health" ], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.8, "score_meta_tooling": 2.3, "score_tech_depth": 1.5, "score_demo": 2.5, "score_total": 8.1, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ], [ "Open-weights / fine-tuning", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (15)", "+0.4" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Automated CI workflow", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Video walkthrough", "+1.1" ], [ "Reproducible setup guide", "+0.4" ], [ "Live web deployment", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 26, "is_new": false, "commits_delta": 6, "rank_delta": 17, "commits_delta_last_run": 0 }, { "full_name": "nikolareljin/orphan-parts", "html_url": "https://github.com/nikolareljin/orphan-parts", "track": "Build for Your World", "domain": "Business, Sales & Commerce", "summary": "Scans owned items to suggest reuse, missing Marketplace parts, and resale prep", "readme_summary": "Orphan Parts Lens inventories scanned objects and gives evidence-backed reuse or resale answers. Finds missing pieces on Marketplace or preps listings. Built with Android, backend API and hosted app on Muse models.", "tech_highlights": [ "Muse Models API", "Vision Inventory Scan", "Android + Backend" ], "created_at": "2026-10-27T18:07:12Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 479, "commits_before_window": 0, "prs_total": 106, "prs_merged": 92, "is_preexisting": false, "has_docker": true, "has_tests": false, "has_src": true, "has_ci": true, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": true, "has_eval_benchmarks": true, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": true, "live_urls": [ "https://nikolareljin.github.io/orphan-parts/project/flow/", "https://nikolareljin.github.io/orphan-parts/", "https://orphan-parts.pages.dev", "https://nikolareljin.github.io/orphan-parts/start/pairing/", "https://nikolareljin.github.io/orphan-parts/about/" ], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 1, "score_impact": 2.5, "score_meta_tooling": 2.3, "score_tech_depth": 1.8, "score_demo": 1.4, "score_total": 8.0, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Eval & benchmark proof", "+0.3" ], [ "Docker packaging", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ], [ "Open-weights / fine-tuning", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (479)", "+0.6" ], [ "Modular src/ architecture", "+0.3" ], [ "Agent / eval harness", "+0.2" ], [ "Automated CI workflow", "+0.2" ], [ "PR review workflow (92 PRs)", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Live web deployment", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 27, "is_new": true, "commits_delta": 479, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "creativeheadz/wegweiser-eyewitness", "html_url": "https://github.com/creativeheadz/wegweiser-eyewitness", "track": "Push the Frontier", "domain": "Developer Tooling, Infra & Security", "summary": "Phone camera diagnoses PCs when monitoring agent goes offline", "readme_summary": "Helpdesk tool where phone films PC lights and screens for offline diagnosis. Interprets blink codes like memory failure for technicians. Integrates with existing helpdesk workflows and migrations.", "tech_highlights": [ "Muse Vision", "Python + App", "Helpdesk Integration" ], "created_at": "2026-10-27T12:33:25Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 65, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": true, "has_eval_benchmarks": false, "has_setup_guide": false, "has_video_demo": true, "video_urls": [ "https://youtu.be/fSsAfWAcBeQ" ], "has_live_deploy": true, "live_urls": [ "https://wegweiser.tech" ], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.1, "score_meta_tooling": 2.3, "score_tech_depth": 1.5, "score_demo": 2.1, "score_total": 8.0, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "High-impact domain", "+0.4" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ], [ "Open-weights / fine-tuning", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (65)", "+0.6" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Video walkthrough", "+1.1" ], [ "Live web deployment", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 28, "is_new": false, "commits_delta": 16, "rank_delta": 22, "commits_delta_last_run": 0 }, { "full_name": "seekdaseek/iussum-agent", "html_url": "https://github.com/seekdaseek/iussum-agent", "track": "Push the Frontier", "domain": "Finance, Crypto & Web3", "summary": "Voice-set spending limits for shopping agents with automatic refund evidence", "readme_summary": "Compiles spoken limits into enforced buying policy, shops autonomously and builds vision evidence for refunds on wrong delivery. Built entirely on Meta open-weights Muse Spark Open models on Solana devnet. Node plus Modal architecture.", "tech_highlights": [ "Muse Spark Open", "Voice To Limits", "Solana Devnet Pay" ], "created_at": "2026-10-26T19:19:13Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 29, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": true, "has_eval_benchmarks": true, "has_setup_guide": false, "has_video_demo": true, "video_urls": [ "https://www.youtube.com/watch?v=9CExAnb9XKE" ], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.5, "score_meta_tooling": 2.3, "score_tech_depth": 1.5, "score_demo": 1.7, "score_total": 8.0, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "Domain alignment", "+0.3" ], [ "Eval & benchmark proof", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ], [ "Open-weights / fine-tuning", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (29)", "+0.4" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Agent / eval harness", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Video walkthrough", "+1.1" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 29, "is_new": false, "commits_delta": 10, "rank_delta": 44, "commits_delta_last_run": 0 }, { "full_name": "zariffromlatif/muse-cleanroom", "html_url": "https://github.com/zariffromlatif/muse-cleanroom", "track": "Push the Frontier", "domain": "Developer Tooling, Infra & Security", "summary": "Runtime oversight plugin that keeps secrets from coding agents browsing the web", "readme_summary": "Plugin for Meta Muse Code that enforces the Agents Rule of Two at runtime. It detects untrusted content plus sensitive data in one session and delegates the step to a verified subagent on a Meta model without the secret.", "tech_highlights": [ "Muse Code Plugin", "Muse Spark", "Rule-of-Two Gateway" ], "created_at": "2026-10-27T09:26:40Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 22, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": false, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": true, "has_eval_benchmarks": true, "has_setup_guide": true, "has_video_demo": true, "video_urls": [ "https://youtu.be/V9oeDHIdqKM" ], "has_live_deploy": true, "live_urls": [ "https://zariffromlatif.github.io/muse-cleanroom/" ], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 1, "score_impact": 2.6, "score_meta_tooling": 2.0, "score_tech_depth": 0.9, "score_demo": 2.5, "score_total": 8.0, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "High-impact domain", "+0.4" ], [ "Eval & benchmark proof", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ], [ "Open-weights / fine-tuning", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (22)", "+0.4" ], [ "Agent / eval harness", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Video walkthrough", "+1.1" ], [ "Reproducible setup guide", "+0.4" ], [ "Live web deployment", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 30, "is_new": true, "commits_delta": 22, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "seanudeke/Expectrail", "html_url": "https://github.com/seanudeke/Expectrail", "track": "Push the Frontier", "domain": "Developer Tooling, Infra & Security", "summary": "Verifies AI bug fixes by replaying gameplay and watching frames", "readme_summary": "Tests coding-agent fixes by playing the game and recording replays with frame evidence. Harness with Docker, agents, bench and bugs corpus. Uses Muse Code fixes with engine logs plus screenshot review to accept or reject patches.", "tech_highlights": [ "Muse Code + Review", "Game Replay Harness", "Docker Bench" ], "created_at": "2026-10-27T02:31:33Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 462, "commits_before_window": 0, "prs_total": 175, "prs_merged": 170, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": true, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": true, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": true, "live_urls": [ "https://expectrail.com" ], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.3, "score_meta_tooling": 2.3, "score_tech_depth": 1.9, "score_demo": 1.4, "score_total": 7.9, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "High-impact domain", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ], [ "Open-weights / fine-tuning", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (462)", "+0.6" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Automated CI workflow", "+0.2" ], [ "PR review workflow (170 PRs)", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Live web deployment", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 31, "is_new": true, "commits_delta": 462, "rank_delta": 0, "commits_delta_last_run": 2 }, { "full_name": "DivDev93/OfficeOfOtherwise-MetaHackathon", "html_url": "https://github.com/DivDev93/OfficeOfOtherwise-MetaHackathon", "track": "Build for Your World", "domain": "Gaming, Entertainment & Creative Media", "summary": "Alternate-history workbench that branches what-if premises into illustrated timelines", "readme_summary": "Counterfactual worldbuilding tool for writers turning one premise into navigable event branches. Dockerized harness with saved local replay requiring no credentials. Uses Meta models for consequences and illustrative scenes.", "tech_highlights": [ "Muse Models", "Docker + Local Replay", "Branching Narrative UI" ], "created_at": "2026-10-26T13:15:38Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 161, "commits_before_window": 0, "prs_total": 11, "prs_merged": 10, "is_preexisting": false, "has_docker": true, "has_tests": true, "has_src": true, "has_ci": true, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": true, "video_urls": [ "https://github.com/DivDev93/OfficeOfOtherwise-MetaHackathon/releases/download/hackathon-submission-2026-10-31/office-of-otherwise-submission-1080p-v2.mp4" ], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.1, "score_meta_tooling": 1.8, "score_tech_depth": 1.9, "score_demo": 2.1, "score_total": 7.9, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "General domain", "+0.2" ], [ "Docker packaging", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (161)", "+0.6" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Automated CI workflow", "+0.2" ], [ "PR review workflow (10 PRs)", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Video walkthrough", "+1.1" ], [ "Reproducible setup guide", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 32, "is_new": false, "commits_delta": 116, "rank_delta": 8, "commits_delta_last_run": 1 }, { "full_name": "swopno1/vivereply-concierge", "html_url": "https://github.com/swopno1/vivereply-concierge", "track": "Build for Your World", "domain": "Business, Sales & Commerce", "summary": "AI front-of-house for resorts with live booking, pricing and staff handoff", "readme_summary": "Multilingual concierge checks live availability, quotes exact price, holds rooms and links to resort pay page. Unverifiable requests route to staff with transcript. Built with Next.js, Muse Spark, Prisma and voice support.", "tech_highlights": [ "Muse Spark", "Next.js + Prisma", "Bilingual Voice" ], "created_at": "2026-10-26T19:25:55Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 94, "commits_before_window": 0, "prs_total": 11, "prs_merged": 11, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": true, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": true, "has_setup_guide": true, "has_video_demo": true, "video_urls": [ "https://www.youtube.com/watch?v=VIDEO_ID" ], "has_live_deploy": true, "live_urls": [ "https://vivereply-dashboard-md-amir-hossains-projects.vercel.app" ], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 2, "score_impact": 2.1, "score_meta_tooling": 1.3, "score_tech_depth": 2.0, "score_demo": 2.5, "score_total": 7.9, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Eval & benchmark proof", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (94)", "+0.6" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Agent / eval harness", "+0.2" ], [ "Automated CI workflow", "+0.2" ], [ "PR review workflow (11 PRs)", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Video walkthrough", "+1.1" ], [ "Reproducible setup guide", "+0.4" ], [ "Live web deployment", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 33, "is_new": false, "commits_delta": 46, "rank_delta": 110, "commits_delta_last_run": 0 }, { "full_name": "zenith4eva/crew-sync", "html_url": "https://github.com/zenith4eva/crew-sync", "track": "Build for Your World", "domain": "Multimodal Vision & Video (SAM / Vision)", "summary": "Turns one dance rehearsal video into per-dancer sync scores and formation map", "readme_summary": "Tracks every dancer with SAM 3.1, measures beat-by-beat timing vs crew and checks top-down formation. Outputs coach notes on who to fix first plus 20-sec Sync Score Reel. Python 3.11 backend with frontend, pytest and evals.", "tech_highlights": [ "SAM 3.1 Vision", "Muse Spark 1.3", "Python + pytest" ], "created_at": "2026-10-27T14:29:37Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 41, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": true, "has_tests": true, "has_src": true, "has_ci": true, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": true, "has_setup_guide": true, "has_video_demo": true, "video_urls": [ "https://github.com/zenith4eva/crew-sync/releases/download/demo/crew-sync-demo.mp4" ], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.5, "score_meta_tooling": 1.6, "score_tech_depth": 1.7, "score_demo": 2.1, "score_total": 7.9, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Eval & benchmark proof", "+0.3" ], [ "Docker packaging", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (41)", "+0.4" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Agent / eval harness", "+0.2" ], [ "Automated CI workflow", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Video walkthrough", "+1.1" ], [ "Reproducible setup guide", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 34, "is_new": false, "commits_delta": 19, "rank_delta": -6, "commits_delta_last_run": 0 }, { "full_name": "phil10xs/vergefield-os", "html_url": "https://github.com/phil10xs/vergefield-os", "track": "Build for Your World", "domain": "Business, Sales & Commerce", "summary": "Films property issues to get costed snag list and bills tracker board", "readme_summary": "VergeCare Beta turns narrated repair video into costed snag list with Issues and Bills Tracker. Next.js + Drizzle + Docker stack with evals, source-available build of hosted demo. Uses Meta multimodal models for end-to-end agentic vision, narration and costing.", "tech_highlights": [ "Multimodal Agentic AI", "Next.js + Drizzle", "Meta Vision Models" ], "created_at": "2026-10-29T04:55:14Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 38, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": true, "has_tests": true, "has_src": true, "has_ci": true, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": true, "has_setup_guide": true, "has_video_demo": true, "video_urls": [ "https://youtu.be/aHLs56BK9LY", "https://drive.google.com/file/d/1p7-j7FmEnigX8hcyw3_3Y5EYsvBroqC2", "https://drive.google.com/file/d/1Zm9FlpDPe27eUYOts5ier8eIkeoWOJz1", "https://www.youtube.com/watch?v=aHLs56BK9LY" ], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 6, "score_impact": 2.5, "score_meta_tooling": 1.6, "score_tech_depth": 1.7, "score_demo": 2.1, "score_total": 7.9, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Eval & benchmark proof", "+0.3" ], [ "Docker packaging", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (38)", "+0.4" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Agent / eval harness", "+0.2" ], [ "Automated CI workflow", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Video walkthrough", "+1.1" ], [ "Reproducible setup guide", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 35, "is_new": true, "commits_delta": 38, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "phil10xs/vergecare-meta", "html_url": "https://github.com/phil10xs/vergecare-meta", "track": "Build for Your World", "domain": "Business, Sales & Commerce", "summary": "Films property repair issues to generate costed snag list and tracker", "readme_summary": "VergeCare lets users film and narrate repair issues to get a costed snag list plus Issues and Bills board. Multimodal agentic flow with Next.js frontend, Drizzle and Docker stack. Live demo hosted.", "tech_highlights": [ "Multimodal AI Agent", "Next.js + Drizzle", "Video Understanding" ], "created_at": "2026-10-29T04:55:14Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 38, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": true, "has_tests": true, "has_src": true, "has_ci": true, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": true, "has_setup_guide": true, "has_video_demo": true, "video_urls": [ "https://youtu.be/aHLs56BK9LY", "https://drive.google.com/file/d/1p7-j7FmEnigX8hcyw3_3Y5EYsvBroqC2", "https://drive.google.com/file/d/1Zm9FlpDPe27eUYOts5ier8eIkeoWOJz1" ], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 6, "score_impact": 2.5, "score_meta_tooling": 1.6, "score_tech_depth": 1.7, "score_demo": 2.1, "score_total": 7.9, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Eval & benchmark proof", "+0.3" ], [ "Docker packaging", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (38)", "+0.4" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Agent / eval harness", "+0.2" ], [ "Automated CI workflow", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Video walkthrough", "+1.1" ], [ "Reproducible setup guide", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 36, "is_new": true, "commits_delta": 38, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "alined-labs/vitrina", "html_url": "https://github.com/alined-labs/vitrina", "track": "Build for Your World", "domain": "Business, Sales & Commerce", "summary": "Closed-loop WhatsApp storefront turning seller photos into ads and sales.", "readme_summary": "Vitrina lets Colombian WhatsApp sellers upload photos, prices and FAQs to generate catalog and ads. Stack is Python/FastAPI with Docker plus WhatsApp integration. Uses SAM 3.1 for product cutout, Muse Image for ad scenes and Muse Spark for sales chat.", "tech_highlights": [ "SAM 3.1 Vision", "Muse Spark 1.3", "Muse Image + WhatsApp" ], "created_at": "2026-10-27T06:24:58Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 141, "commits_before_window": 0, "prs_total": 140, "prs_merged": 140, "is_preexisting": false, "has_docker": true, "has_tests": true, "has_src": true, "has_ci": true, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": true, "has_eval_benchmarks": true, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.5, "score_meta_tooling": 2.3, "score_tech_depth": 2.0, "score_demo": 1.0, "score_total": 7.8, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Eval & benchmark proof", "+0.3" ], [ "Docker packaging", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ], [ "Open-weights / fine-tuning", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (141)", "+0.6" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Agent / eval harness", "+0.2" ], [ "Automated CI workflow", "+0.2" ], [ "PR review workflow (140 PRs)", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 37, "is_new": false, "commits_delta": 34, "rank_delta": -19, "commits_delta_last_run": 0 }, { "full_name": "Hisernberg/spanguard", "html_url": "https://github.com/Hisernberg/spanguard", "track": "Push the Frontier", "domain": "Developer Tooling, Infra & Security", "summary": "Span-level guard that strips prompt injections from agent tool outputs.", "readme_summary": "OpenAI-compatible security gateway that scans tool results and MCP payloads. Uses fine-tuned open-weights span model with benchmarks vs Llama Prompt Guard 2. Deploys via Docker/Compose with eval harness.", "tech_highlights": [ "Span Injection Detection", "Muse Spark 1.3", "Docker + FastAPI" ], "created_at": "2026-11-01T14:35:21Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 32, "commits_before_window": 0, "prs_total": 1, "prs_merged": 1, "is_preexisting": false, "has_docker": true, "has_tests": true, "has_src": true, "has_ci": true, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": true, "has_eval_benchmarks": true, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 3.0, "score_meta_tooling": 2.1, "score_tech_depth": 1.7, "score_demo": 1.0, "score_total": 7.8, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "High-impact domain", "+0.4" ], [ "Eval & benchmark proof", "+0.3" ], [ "Docker packaging", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "Open-weights / fine-tuning", "+0.5" ], [ "Published HF Hub weights", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (32)", "+0.4" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Agent / eval harness", "+0.2" ], [ "Automated CI workflow", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 38, "is_new": true, "commits_delta": 32, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "donovan-ratefison/Zotra", "html_url": "https://github.com/donovan-ratefison/Zotra", "track": "Build for Your World", "domain": "Finance, Crypto & Web3", "summary": "Studio that turns bank credit policy PDFs into tested auditable approval apps", "readme_summary": "Converts credit policy documents into a working approval app with AI-drafted workflows and tests. Humans review and decide while every rule is auditable. Go backend with Docker Compose deployment and CI releases.", "tech_highlights": [ "Muse Spark", "Go + Docker", "Policy-to-App" ], "created_at": "2026-10-26T16:29:48Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 179, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": true, "has_tests": false, "has_src": true, "has_ci": true, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": true, "video_urls": [ "https://www.youtube.com/watch?v=FBQbIOHB1C8" ], "has_live_deploy": true, "live_urls": [ "https://zotra-demo.donovan-ratefison.mg" ], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.2, "score_meta_tooling": 1.6, "score_tech_depth": 1.4, "score_demo": 2.5, "score_total": 7.7, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Docker packaging", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (179)", "+0.6" ], [ "Modular src/ architecture", "+0.3" ], [ "Automated CI workflow", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Video walkthrough", "+1.1" ], [ "Reproducible setup guide", "+0.4" ], [ "Live web deployment", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 39, "is_new": true, "commits_delta": 179, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "coder-RT/recall", "html_url": "https://github.com/coder-RT/recall", "track": "Build for Your World", "domain": "Healthcare, Civic Tech & Sustainability", "summary": "Voice-first 3D home memory that guides blind users back to lost items", "readme_summary": "Walk through once to map home, then ask where items are and get step-by-step voice directions with camera verification. JS monorepo with evals. Uses SAM 3.1, MapAnything, and Muse Glimmer.", "tech_highlights": [ "SAM 3.1 Vision", "MapAnything 3D", "Muse Glimmer Voice" ], "created_at": "2026-10-26T19:47:20Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 122, "commits_before_window": 0, "prs_total": 10, "prs_merged": 10, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": true, "has_ci": true, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": true, "has_eval_benchmarks": true, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": true, "live_urls": [ "https://recall-ten-khaki.vercel.app" ], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.2, "score_meta_tooling": 2.3, "score_tech_depth": 1.8, "score_demo": 1.4, "score_total": 7.7, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "High-impact domain", "+0.4" ], [ "Eval & benchmark proof", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ], [ "Open-weights / fine-tuning", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (122)", "+0.6" ], [ "Modular src/ architecture", "+0.3" ], [ "Agent / eval harness", "+0.2" ], [ "Automated CI workflow", "+0.2" ], [ "PR review workflow (10 PRs)", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Live web deployment", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 40, "is_new": false, "commits_delta": 121, "rank_delta": 404, "commits_delta_last_run": 0 }, { "full_name": "prashanth-ds-ml/anubhav", "html_url": "https://github.com/prashanth-ds-ml/anubhav", "track": "Build for Your World", "domain": "Autonomous Agents & Workflow Automation", "summary": "Multilingual Telugu logistics agent that learns unwritten rules from trip history", "readme_summary": "Dispatcher agent takes Telugu, Roman Telugu or English text and voice to plan trips over company data. Mines trip history for rules, verifies with code and human approval for reuse. Built on Meta Muse with Streamlit, Docker and shared regional knowledge.", "tech_highlights": [ "Muse Models", "Voice + Telugu", "Streamlit + Docker" ], "created_at": "2026-10-26T20:23:38Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 121, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": true, "has_tests": true, "has_src": true, "has_ci": true, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": true, "has_eval_benchmarks": true, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": true, "live_urls": [ "https://anubhav-metahackathon.streamlit.app/" ], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.6, "score_meta_tooling": 1.8, "score_tech_depth": 1.9, "score_demo": 1.4, "score_total": 7.7, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "High-impact domain", "+0.4" ], [ "Eval & benchmark proof", "+0.3" ], [ "Docker packaging", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "Open-weights / fine-tuning", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (121)", "+0.6" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Agent / eval harness", "+0.2" ], [ "Automated CI workflow", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Live web deployment", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 41, "is_new": false, "commits_delta": 89, "rank_delta": 294, "commits_delta_last_run": 0 }, { "full_name": "seanudeke/Nightshift", "html_url": "https://github.com/seanudeke/Nightshift", "track": "Push the Frontier", "domain": "Developer Tooling, Infra & Security", "summary": "Verifies AI bug fixes by replaying gameplay and watching frames", "readme_summary": "Repo mirrors Expectrail harness that replays game fixes and judges with recorded frames. Same Docker harness, agents, and bench structure. Uses Muse Code and visual replay review to catch fixes that pass logs but fail visually.", "tech_highlights": [ "Muse Code + Review", "Game Replay Harness", "Docker Bench" ], "created_at": "2026-10-27T02:31:33Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 462, "commits_before_window": 0, "prs_total": 175, "prs_merged": 170, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": false, "has_ci": true, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": true, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": true, "live_urls": [ "https://expectrail.com" ], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.3, "score_meta_tooling": 2.3, "score_tech_depth": 1.6, "score_demo": 1.4, "score_total": 7.6, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "High-impact domain", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ], [ "Open-weights / fine-tuning", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (462)", "+0.6" ], [ "Automated test suite", "+0.3" ], [ "Automated CI workflow", "+0.2" ], [ "PR review workflow (170 PRs)", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Live web deployment", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 42, "is_new": true, "commits_delta": 462, "rank_delta": 0, "commits_delta_last_run": 2 }, { "full_name": "Gruya13/codeproof", "html_url": "https://github.com/Gruya13/codeproof", "track": "Push the Frontier", "domain": "Developer Tooling, Infra & Security", "summary": "Static JS reviewer where every finding ships with verified citations or failing tests", "readme_summary": "Producer model proposes TypeScript findings, deterministic checker verifies citations, second model tries refutation. Dockerized pipeline publishes verified or execution-proven labels; uses Meta Muse models.", "tech_highlights": [ "Muse Spark", "Static Analysis + LLM", "Docker + TypeScript" ], "created_at": "2026-10-26T18:25:43Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 227, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": true, "has_tests": true, "has_src": true, "has_ci": true, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": true, "video_urls": [ "https://youtu.be/pFNrljVBJh0" ], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.7, "score_meta_tooling": 1.1, "score_tech_depth": 1.7, "score_demo": 2.1, "score_total": 7.6, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "High-impact domain", "+0.4" ], [ "Docker packaging", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (227)", "+0.6" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Automated CI workflow", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Video walkthrough", "+1.1" ], [ "Reproducible setup guide", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 43, "is_new": false, "commits_delta": 101, "rank_delta": -7, "commits_delta_last_run": 0 }, { "full_name": "CipherPRG/onboardiq", "html_url": "https://github.com/CipherPRG/onboardiq", "track": "Push the Frontier", "domain": "Developer Tooling, Infra & Security", "summary": "Agent that onboards network devices by reading manuals and proving metrics live", "readme_summary": "Muse Spark reads MIB files to pick objects for CPU, memory, disk and thermal health. Each pick is tested live on device for existence, type, range and load behavior, retrying with evidence. Only proven picks are scored and explained.", "tech_highlights": [ "Muse Spark", "SNMP + MIB Parser", "Live Verification" ], "created_at": "2026-10-26T21:12:51Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 174, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": true, "has_tests": true, "has_src": true, "has_ci": true, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": true, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": true, "live_urls": [ "https://cipherprg.github.io/onboardiq/" ], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 3.0, "score_meta_tooling": 1.3, "score_tech_depth": 1.9, "score_demo": 1.4, "score_total": 7.6, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "High-impact domain", "+0.4" ], [ "Eval & benchmark proof", "+0.3" ], [ "Docker packaging", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (174)", "+0.6" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Agent / eval harness", "+0.2" ], [ "Automated CI workflow", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Live web deployment", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 44, "is_new": false, "commits_delta": 82, "rank_delta": 3, "commits_delta_last_run": 2 }, { "full_name": "DhabtPlatform/souk-lens-indie", "html_url": "https://github.com/DhabtPlatform/souk-lens-indie", "track": "Build for Your World", "domain": "Business, Sales & Commerce", "summary": "Turns souk stall photos into grounded listings tied to numbered boxes.", "readme_summary": "Souk Lens analyzes market stall photos into item listings bound to SAM 3.1 boxes drawn on the photo. Built with Next.js and Vercel with one-click demo pipeline. Uses SAM 3.1 for grounding and Muse Spark 1.3 for box-referenced descriptions.", "tech_highlights": [ "SAM 3.1 Grounding", "Muse Spark 1.3", "Next.js + Vercel" ], "created_at": "2026-10-27T04:51:45Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 88, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": true, "video_urls": [ "https://youtu.be/J2DEuiJ1cDU" ], "has_live_deploy": true, "live_urls": [ "https://souk-lens-indie.vercel.app" ], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.8, "score_meta_tooling": 1.8, "score_tech_depth": 1.5, "score_demo": 2.5, "score_total": 7.6, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (88)", "+0.6" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Video walkthrough", "+1.1" ], [ "Reproducible setup guide", "+0.4" ], [ "Live web deployment", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 45, "is_new": false, "commits_delta": 24, "rank_delta": 3, "commits_delta_last_run": 0 }, { "full_name": "Bhav-ikkk/spectra", "html_url": "https://github.com/Bhav-ikkk/spectra", "track": "Push the Frontier", "domain": "Developer Tooling, Infra & Security", "summary": "Visual referee that verifies AI coding agent UI work with optics.", "readme_summary": "Spectra provides CLI, MCP and Workbench to double-check frontend agent output using SAM 3.1 plus Pixel NCC calibrated to 3-sigma noise floor. Includes 138 offline tests and benchmark reports.", "tech_highlights": [ "SAM 3.1 Vision", "Pixel NCC Check", "MCP + CLI" ], "created_at": "2026-10-26T14:41:26Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 60, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": true, "has_tests": true, "has_src": true, "has_ci": true, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": true, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": true, "live_urls": [ "https://spectra-lyart.vercel.app" ], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 3.0, "score_meta_tooling": 1.3, "score_tech_depth": 1.9, "score_demo": 1.4, "score_total": 7.6, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "High-impact domain", "+0.4" ], [ "Eval & benchmark proof", "+0.3" ], [ "Docker packaging", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (60)", "+0.6" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Agent / eval harness", "+0.2" ], [ "Automated CI workflow", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Live web deployment", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 46, "is_new": true, "commits_delta": 60, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "aauthier2385/dealer-social-ai-hackathon", "html_url": "https://github.com/aauthier2385/dealer-social-ai-hackathon", "track": "Build for Your World", "domain": "Business, Sales & Commerce", "summary": "Memory agent that preserves dealership customer relationships across staff", "readme_summary": "Relationship-memory agent for car dealerships keeps customer history when salespeople leave. Built on Muse Spark 1.3 with Muse Voice Transcribe, SAM 3.1 and Muse Image. Includes 172 tests, ruff, gitleaks and CI with live demo.", "tech_highlights": [ "Muse Spark 1.3", "SAM 3.1 + Muse Image", "Voice Transcribe" ], "created_at": "2026-10-26T21:37:28Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 27, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": true, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": true, "video_urls": [ "https://www.youtube.com/watch?v=KAK70NaoxkU" ], "has_live_deploy": true, "live_urls": [ "https://dealer-social-demo.onrender.com" ], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 1, "score_impact": 1.8, "score_meta_tooling": 1.8, "score_tech_depth": 1.5, "score_demo": 2.5, "score_total": 7.6, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (27)", "+0.4" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Automated CI workflow", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Video walkthrough", "+1.1" ], [ "Reproducible setup guide", "+0.4" ], [ "Live web deployment", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 47, "is_new": true, "commits_delta": 27, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "gokhunyayla/muse-servicedesk", "html_url": "https://github.com/gokhunyayla/muse-servicedesk", "track": "Build for Your World", "domain": "Autonomous Agents & Workflow Automation", "summary": "Multi-tier IT service desk agents acting over WhatsApp and email", "readme_summary": "Four L1-L4 agents fix IT issues via tool calls to Microsoft 365, Azure VM and VPN plus proactive monitoring. Uses Meta Model API with FastAPI app, agent framework and tests for approvals and identity checks.", "tech_highlights": [ "Meta Model API", "Multi-Agent L1-L4", "WhatsApp + M365 Tools" ], "created_at": "2026-10-27T07:08:04Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 193, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": true, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": true, "video_urls": [ "https://youtu.be/rMqozO4E0ng" ], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 1, "score_impact": 1.9, "score_meta_tooling": 1.8, "score_tech_depth": 1.7, "score_demo": 2.1, "score_total": 7.5, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "High-impact domain", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (193)", "+0.6" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Automated CI workflow", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Video walkthrough", "+1.1" ], [ "Reproducible setup guide", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 48, "is_new": false, "commits_delta": 21, "rank_delta": -36, "commits_delta_last_run": 0 }, { "full_name": "momoikura/The-Polisher", "html_url": "https://github.com/momoikura/The-Polisher", "track": "Push the Frontier", "domain": "Developer Tooling, Infra & Security", "summary": "Turns GitHub issues into tested pull requests verified in sandbox", "readme_summary": "The-Polisher generates fixes from GitHub issues, runs pytest in Modal sandbox and adversarially tests them. Stack is TypeScript React frontend with Cloudflare Pages and Python targets. Uses Muse Spark for code generation and Muse Wonder for break-attempts.", "tech_highlights": [ "Muse Spark", "Muse Wonder", "Modal Sandbox" ], "created_at": "2026-10-28T09:53:20Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 119, "commits_before_window": 0, "prs_total": 1, "prs_merged": 1, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": true, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": true, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": true, "live_urls": [ "https://thepolisher.pages.dev", "https://thepolisher.pages.dev/runs/09e2e317-527f-44dd-8b38-52723ce52230", "https://thepolisher.pages.dev/runs", "https://thepolisher.pages.dev/runs/b1eb802c-5e3b-42f5-8ba5-7859e88d0117" ], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 2, "score_impact": 2.6, "score_meta_tooling": 1.6, "score_tech_depth": 1.9, "score_demo": 1.4, "score_total": 7.5, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "High-impact domain", "+0.4" ], [ "Eval & benchmark proof", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (119)", "+0.6" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Agent / eval harness", "+0.2" ], [ "Automated CI workflow", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Live web deployment", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 49, "is_new": true, "commits_delta": 119, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "hosbe1/Proof-Carrying-Code-Meta-AI-Hackathon-2026", "html_url": "https://github.com/hosbe1/Proof-Carrying-Code-Meta-AI-Hackathon-2026", "track": "Push the Frontier", "domain": "Developer Tooling, Infra & Security", "summary": "Converts Python functions to verified Dafny code or concrete counterexamples", "readme_summary": "Pipeline infers intent without seeing body, writes executable spec, transpiles to Dafny via rules plus model fallback and proves with staged prover. Emits verifiable Dafny proof or runnable Python failing test. Python package with GitHub Action, docs and training code.", "tech_highlights": [ "Muse Models", "Dafny Verifier", "Python Transpiler" ], "created_at": "2026-10-27T20:36:24Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 94, "commits_before_window": 0, "prs_total": 81, "prs_merged": 80, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": true, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": true, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 1, "score_impact": 2.3, "score_meta_tooling": 2.3, "score_tech_depth": 1.9, "score_demo": 1.0, "score_total": 7.5, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "High-impact domain", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ], [ "Open-weights / fine-tuning", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (94)", "+0.6" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Automated CI workflow", "+0.2" ], [ "PR review workflow (80 PRs)", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 50, "is_new": false, "commits_delta": 77, "rank_delta": 120, "commits_delta_last_run": 0 }, { "full_name": "raahimnawaz/workbench-copilot", "html_url": "https://github.com/raahimnawaz/workbench-copilot", "track": "Push the Frontier", "domain": "Robotics, IoT & Manufacturing", "summary": "Voice-driven lab assistant that reads breadboards and guides SO-101 arm.", "readme_summary": "Workbench Co-Pilot is a hands-free lab partner in the editor and on the bench. Python router in wbc/agent dispatches to coder, vision and voice tools plus SO-101 control. Uses Muse Spark routing to Muse Wonder, SAM 3.1 and Voice Transcribe.", "tech_highlights": [ "Muse Spark Router", "SAM 3.1 Vision", "SO-101 Arm" ], "created_at": "2026-10-26T21:50:59Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 88, "commits_before_window": 0, "prs_total": 22, "prs_merged": 22, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": true, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": true, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.3, "score_meta_tooling": 2.3, "score_tech_depth": 1.9, "score_demo": 1.0, "score_total": 7.5, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "High-impact domain", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ], [ "Open-weights / fine-tuning", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (88)", "+0.6" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Automated CI workflow", "+0.2" ], [ "PR review workflow (22 PRs)", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 51, "is_new": false, "commits_delta": 10, "rank_delta": -29, "commits_delta_last_run": 0 }, { "full_name": "DrVelvetFog/agent-andy", "html_url": "https://github.com/DrVelvetFog/agent-andy", "track": "Push the Frontier", "domain": "Developer Tooling, Infra & Security", "summary": "A rule-checking agent that logs every action in hash-chained receipts.", "readme_summary": "Agent Andy checks local rules like metal-detecting permissions before acting, writing hash-chained receipts. A deterministic policy engine verifies actions separately, with replayable browser verification.", "tech_highlights": [ "Hash-Chained Receipts", "Policy Engine", "Muse Agent" ], "created_at": "2026-10-26T12:59:24Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 59, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": true, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": true, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": true, "live_urls": [ "https://drvelvetfog.github.io/agent-andy/" ], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.6, "score_meta_tooling": 1.6, "score_tech_depth": 1.9, "score_demo": 1.4, "score_total": 7.5, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "High-impact domain", "+0.4" ], [ "Eval & benchmark proof", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (59)", "+0.6" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Agent / eval harness", "+0.2" ], [ "Automated CI workflow", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Live web deployment", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 52, "is_new": false, "commits_delta": 35, "rank_delta": 96, "commits_delta_last_run": 0 }, { "full_name": "Zakariachirah/darflow-agent", "html_url": "https://github.com/Zakariachirah/darflow-agent", "track": "Build for Your World", "domain": "Business, Sales & Commerce", "summary": "WhatsApp guest concierge and expense agent for small Moroccan riads", "readme_summary": "Runs WhatsApp front desk in any language plus expense back-office with manager inbox for 5-10 room riads. Node.js src with importer, docs and evals integrating with closed-source DarFlow. Uses Muse models plus SAM 3.1 and Muse Voice Transcribe for receipts.", "tech_highlights": [ "Muse Spark", "SAM 3.1 + Voice", "WhatsApp Agent" ], "created_at": "2026-10-26T16:26:38Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 36, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": true, "has_setup_guide": true, "has_video_demo": true, "video_urls": [ "https://youtu.be/1eJox7rG1Hk" ], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.1, "score_meta_tooling": 1.8, "score_tech_depth": 1.5, "score_demo": 2.1, "score_total": 7.5, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Eval & benchmark proof", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (36)", "+0.4" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Agent / eval harness", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Video walkthrough", "+1.1" ], [ "Reproducible setup guide", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 53, "is_new": false, "commits_delta": 6, "rank_delta": -44, "commits_delta_last_run": 0 }, { "full_name": "jeejak/proofmuse", "html_url": "https://github.com/jeejak/proofmuse", "track": "Build for Your World", "domain": "Multimodal Vision & Video (SAM / Vision)", "summary": "Checks packing photos for marketplace dispute evidence quality", "readme_summary": "Seller uploads packing photo, gets Indonesian feedback in seconds on label and evidence issues. Go backend where models observe and rules engine decides, with eval set. Uses Muse Spark 1.3 and SAM 3.1 label boxes.", "tech_highlights": [ "Muse Spark 1.3", "SAM 3.1 Vision", "Go Rules Engine" ], "created_at": "2026-10-26T09:32:43Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 32, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": true, "has_tests": false, "has_src": false, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": true, "has_setup_guide": true, "has_video_demo": true, "video_urls": [ "https://youtu.be/OJSj9r7RKPY" ], "has_live_deploy": true, "live_urls": [ "https://proofmuse.jeejak.id" ], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.5, "score_meta_tooling": 1.6, "score_tech_depth": 0.9, "score_demo": 2.5, "score_total": 7.5, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Eval & benchmark proof", "+0.3" ], [ "Docker packaging", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (32)", "+0.4" ], [ "Agent / eval harness", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Video walkthrough", "+1.1" ], [ "Reproducible setup guide", "+0.4" ], [ "Live web deployment", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 54, "is_new": true, "commits_delta": 32, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "mrdzyn/proofpilot-ai", "html_url": "https://github.com/mrdzyn/proofpilot-ai", "track": "Push the Frontier", "domain": "Developer Tooling, Infra & Security", "summary": "Proves UI bug fixes with recorded repro and independent verifier retest", "readme_summary": "Turns UI defect recording into browser reproduction, candidate patch and independent re-test. Monorepo with offline scoreboard and staging. Uses Muse Spark 1.3 via Meta Model API for video analysis.", "tech_highlights": [ "Muse Spark 1.3", "Verifier Harness", "Browser Repro" ], "created_at": "2026-10-26T09:24:11Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 27, "commits_before_window": 0, "prs_total": 32, "prs_merged": 26, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": true, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": true, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": true, "live_urls": [ "https://cerebralvalley.ai/e/meta-ai-developer-hackathon/hackathon/" ], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.3, "score_meta_tooling": 2.3, "score_tech_depth": 1.7, "score_demo": 1.2, "score_total": 7.5, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "High-impact domain", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ], [ "Open-weights / fine-tuning", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (27)", "+0.4" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Automated CI workflow", "+0.2" ], [ "PR review workflow (26 PRs)", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Live web deployment", "+0.4" ] ] }, "rank": 55, "is_new": true, "commits_delta": 27, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "athos-agent/athos-meta", "html_url": "https://github.com/athos-agent/athos-meta", "track": "Push the Frontier", "domain": "Developer Tooling, Infra & Security", "summary": "Portable local memory that lets any AI agent reuse your checklists and rules", "readme_summary": "Athos turns user criteria, steps and checklists into living local portable memory. Local-first architecture with installable agent skills and plugins. Uses Muse models to extract and apply personal rules without re-explaining.", "tech_highlights": [ "Muse Spark", "Local-First Memory", "Agent Skills" ], "created_at": "2026-10-31T23:52:30Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 8, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": true, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": true, "has_eval_benchmarks": false, "has_setup_guide": false, "has_video_demo": true, "video_urls": [ "https://youtu.be/4JabA-KajK0" ], "has_live_deploy": true, "live_urls": [ "https://athos-agent.github.io/athos/" ], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.3, "score_meta_tooling": 1.8, "score_tech_depth": 1.3, "score_demo": 2.1, "score_total": 7.5, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "High-impact domain", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ], [ "Open-weights / fine-tuning", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "5+ window commits (8)", "+0.2" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Automated CI workflow", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Video walkthrough", "+1.1" ], [ "Live web deployment", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 56, "is_new": true, "commits_delta": 8, "rank_delta": 0, "commits_delta_last_run": 2 }, { "full_name": "sidonsoft/muse-recall", "html_url": "https://github.com/sidonsoft/muse-recall", "track": "Push the Frontier", "domain": "Developer Tooling, Infra & Security", "summary": "Local-first memory layer that stores and corrects decisions for Muse builds.", "readme_summary": "HTML Studio for Muse Spark that persists project decisions with human review. Evaluated in 480-run trial across Muse models and game builds. Monorepo with apps/packages and browser Codespaces demo.", "tech_highlights": [ "Muse Spark", "Local-first Memory", "TypeScript Monorepo" ], "created_at": "2026-10-26T22:28:17Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 227, "commits_before_window": 0, "prs_total": 266, "prs_merged": 264, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": true, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": true, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": true, "live_urls": [ "https://sidonsoft.github.io/muse-recall/" ], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.3, "score_meta_tooling": 1.8, "score_tech_depth": 1.9, "score_demo": 1.4, "score_total": 7.4, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "High-impact domain", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ], [ "Open-weights / fine-tuning", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (227)", "+0.6" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Automated CI workflow", "+0.2" ], [ "PR review workflow (264 PRs)", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Live web deployment", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 57, "is_new": true, "commits_delta": 227, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "Alehcs/sira", "html_url": "https://github.com/Alehcs/sira", "track": "Push the Frontier", "domain": "General & Emerging Applications", "summary": "AI astronomer that bets on transients and lets data grade predictions", "readme_summary": "SIRA investigates ZTF transients via ALeRCE alerts, proposing rival hypotheses with pre-registered predictions. Keeps a public timestamped ledger and decides when to wait or escalate. Built solo with Muse Spark Open.", "tech_highlights": [ "Muse Spark Open", "ZTF + ALeRCE Data", "Prediction Ledger" ], "created_at": "2026-10-26T23:33:38Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 146, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": true, "has_tests": true, "has_src": true, "has_ci": true, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": true, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": true, "live_urls": [ "https://alehcs.github.io/sira/**", "https://alehcs.github.io/sira/" ], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.5, "score_meta_tooling": 1.8, "score_tech_depth": 1.7, "score_demo": 1.4, "score_total": 7.4, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "General domain", "+0.2" ], [ "Docker packaging", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ], [ "Open-weights / fine-tuning", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (146)", "+0.6" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Automated CI workflow", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Live web deployment", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 58, "is_new": false, "commits_delta": 99, "rank_delta": 311, "commits_delta_last_run": 2 }, { "full_name": "rockyru/regov", "html_url": "https://github.com/rockyru/regov", "track": "Build for Your World", "domain": "Healthcare, Civic Tech & Sustainability", "summary": "Autonomous agent rebuilding legacy PH government sites into accessible experiences.", "readme_summary": "Paste a legacy URL; it crawls pages, understands content and rebuilds on BetterGov Kapwa design system with migration report. Cloudflare plus open-source design system stack. Uses SAM 3.1 and Muse Spark 1.3 via Meta Model API and Muse Image.", "tech_highlights": [ "SAM 3.1 Vision", "Muse Spark 1.3", "Kapwa Design System" ], "created_at": "2026-10-26T21:16:14Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 130, "commits_before_window": 0, "prs_total": 40, "prs_merged": 39, "is_preexisting": false, "has_docker": true, "has_tests": true, "has_src": true, "has_ci": true, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": true, "live_urls": [ "https://regov.app" ], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 5, "score_impact": 2.3, "score_meta_tooling": 1.8, "score_tech_depth": 1.9, "score_demo": 1.4, "score_total": 7.4, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "High-impact domain", "+0.4" ], [ "Docker packaging", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (130)", "+0.6" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Automated CI workflow", "+0.2" ], [ "PR review workflow (39 PRs)", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Live web deployment", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 59, "is_new": false, "commits_delta": 0, "rank_delta": -42, "commits_delta_last_run": 0 }, { "full_name": "wayneherrington/veevee", "html_url": "https://github.com/wayneherrington/veevee", "track": "Build for Your World", "domain": "Voice, Speech & Audio AI", "summary": "Browser voice companion that speaks answers and checks sources before responding", "readme_summary": "PWA companion with no account that answers out loud and cites sources to avoid guessing. Calls Muse Wonder and five other Meta models directly via Meta API with user key.", "tech_highlights": [ "Muse Wonder 1.0", "Meta Model API Direct", "PWA Voice Chat" ], "created_at": "2026-10-27T02:11:27Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 124, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": false, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": true, "has_eval_benchmarks": true, "has_setup_guide": false, "has_video_demo": true, "video_urls": [ "https://youtu.be/8zY0_8KRPkE" ], "has_live_deploy": true, "live_urls": [ "https://wayneherrington.github.io/veevee/" ], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 3, "score_impact": 1.9, "score_meta_tooling": 2.3, "score_tech_depth": 1.1, "score_demo": 2.1, "score_total": 7.4, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Eval & benchmark proof", "+0.3" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ], [ "Open-weights / fine-tuning", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (124)", "+0.6" ], [ "Agent / eval harness", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Video walkthrough", "+1.1" ], [ "Live web deployment", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 60, "is_new": true, "commits_delta": 124, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "Blue-Ocean-Solutions/TinyTMS", "html_url": "https://github.com/Blue-Ocean-Solutions/TinyTMS", "track": "Build for Your World", "domain": "Business, Sales & Commerce", "summary": "Dock check-in that cross-checks vision, paper and voice to sign a freight receipt", "readme_summary": "Three witnesses report load count: SAM 3.1 for vision, Muse Spark 1.3 for document vision, Muse Voice Transcribe for driver voice. Deterministic Python judge in tinytms/verify.py decides HOLD or OK and signs receipt.", "tech_highlights": [ "SAM 3.1 Vision", "Muse Spark 1.3", "Muse Voice Transcribe" ], "created_at": "2026-10-28T15:09:05Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 60, "commits_before_window": 0, "prs_total": 21, "prs_merged": 20, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": true, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": true, "has_eval_benchmarks": true, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.1, "score_meta_tooling": 2.3, "score_tech_depth": 2.0, "score_demo": 1.0, "score_total": 7.4, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Eval & benchmark proof", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ], [ "Open-weights / fine-tuning", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (60)", "+0.6" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Agent / eval harness", "+0.2" ], [ "Automated CI workflow", "+0.2" ], [ "PR review workflow (20 PRs)", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 61, "is_new": false, "commits_delta": 45, "rank_delta": 27, "commits_delta_last_run": 0 }, { "full_name": "bamontejano1978-beep/integrity-harness", "html_url": "https://github.com/bamontejano1978-beep/integrity-harness", "track": "Push the Frontier", "domain": "Developer Tooling, Infra & Security", "summary": "Signed offline-verifiable harness for testing agent behavior under pressure", "readme_summary": "Evaluates situational-pressure scenarios against a deterministic contract and packages results as Ed25519-signed evidence. Includes offline verifier, saved Meta target-agent run, demo app, and judges path requiring no API key.", "tech_highlights": [ "Ed25519 Signed Evidence", "Offline Verifier", "Agent Eval Harness" ], "created_at": "2026-10-27T05:32:21Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 28, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": true, "has_tests": true, "has_src": true, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": true, "video_urls": [ "https://youtu.be/gfuXbeZF058" ], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.7, "score_meta_tooling": 1.3, "score_tech_depth": 1.3, "score_demo": 2.1, "score_total": 7.4, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "High-impact domain", "+0.4" ], [ "Docker packaging", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (28)", "+0.4" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Video walkthrough", "+1.1" ], [ "Reproducible setup guide", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 62, "is_new": false, "commits_delta": 27, "rank_delta": 292, "commits_delta_last_run": 0 }, { "full_name": "louislafosse/jojo", "html_url": "https://github.com/louislafosse/jojo", "track": "Build for Your World", "domain": "Autonomous Agents & Workflow Automation", "summary": "Mac desktop assistant with 3D mascot that answers and automates apps", "readme_summary": "Native Swift Mac assistant with streaming answers, web search, screen-aware planning and in-folder code building. Uses Meta models via API for planning and Muse Code actions without taking over mouse.", "tech_highlights": [ "Swift Mac App", "Muse Models", "On-device Automation" ], "created_at": "2026-11-01T14:44:42Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 4, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": true, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": true, "has_setup_guide": true, "has_video_demo": true, "video_urls": [ "https://youtu.be/t1AZFQDP-7E" ], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.2, "score_meta_tooling": 1.8, "score_tech_depth": 1.3, "score_demo": 2.1, "score_total": 7.4, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "High-impact domain", "+0.4" ], [ "Eval & benchmark proof", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ] ], "tech": [ [ "Base", "+0.3" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Agent / eval harness", "+0.2" ], [ "Automated CI workflow", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Video walkthrough", "+1.1" ], [ "Reproducible setup guide", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 63, "is_new": true, "commits_delta": 4, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "Farshadmhd/beampilot", "html_url": "https://github.com/Farshadmhd/beampilot", "track": "Push the Frontier", "domain": "Autonomous Agents & Workflow Automation", "summary": "Agentic laser M2 measurement to ISO 11146 that rejects bad data honestly", "readme_summary": "Agent drives simulated camera and stage, judges exposure quality, fits caustics until ISO 11146 coverage is met. Python stack with tests and scripts. Uses Muse Spark for agency and SAM 3.1 for vision checks.", "tech_highlights": [ "Muse Spark 1.3", "SAM 3.1 Vision", "Python Agent + ISO 11146" ], "created_at": "2026-10-26T16:49:03Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 168, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": true, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": true, "live_urls": [ "https://farshadm-beampilot.hf.space" ], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.3, "score_meta_tooling": 1.9, "score_tech_depth": 1.7, "score_demo": 1.4, "score_total": 7.3, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "High-impact domain", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "Published HF Hub weights", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (168)", "+0.6" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Automated CI workflow", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Live web deployment", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 64, "is_new": false, "commits_delta": 51, "rank_delta": 102, "commits_delta_last_run": 0 }, { "full_name": "Jaycee871/FrontierLab-Meta-Hackathon-2026", "html_url": "https://github.com/Jaycee871/FrontierLab-Meta-Hackathon-2026", "track": "Push the Frontier", "domain": "Healthcare, Civic Tech & Sustainability", "summary": "Multi-agent assistant turns biomedical questions into cited research plans", "readme_summary": "FrontierLab decomposes biomedical questions into falsifiable hypotheses with mandatory citations and human gates. Built with Python and Streamlit with Hugging Face deployment. Uses Muse models via live provider layer for agents and verification.", "tech_highlights": [ "Muse Models", "Multi-Agent System", "Streamlit + HF" ], "created_at": "2026-10-27T11:26:49Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 136, "commits_before_window": 0, "prs_total": 37, "prs_merged": 32, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": true, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": true, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 1, "score_impact": 2.3, "score_meta_tooling": 2.1, "score_tech_depth": 1.9, "score_demo": 1.0, "score_total": 7.3, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "High-impact domain", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "Open-weights / fine-tuning", "+0.5" ], [ "Published HF Hub weights", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (136)", "+0.6" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Automated CI workflow", "+0.2" ], [ "PR review workflow (32 PRs)", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 65, "is_new": false, "commits_delta": 30, "rank_delta": 24, "commits_delta_last_run": 0 }, { "full_name": "hungtruongOwolf/throughline", "html_url": "https://github.com/hungtruongOwolf/throughline", "track": "Build for Your World", "domain": "Healthcare, Civic Tech & Sustainability", "summary": "Agent fleet guiding cancer patients from referral through visit to follow-up", "readme_summary": "Follows oncology visits from faxed referral, insurance, scheduling, wayfinding to follow-up. Monorepo with multi-hospital demo and role logins plus patient app. Uses Meta AI agents for admin work with human sign-off at key steps.", "tech_highlights": [ "Multi-Agent Fleet", "Next.js on Vercel", "Meta AI Agents" ], "created_at": "2026-10-31T04:20:31Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 80, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": true, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": true, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": true, "live_urls": [ "https://throughline-zeta-ten.vercel.app" ], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.9, "score_meta_tooling": 2.3, "score_tech_depth": 1.7, "score_demo": 1.4, "score_total": 7.3, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "High-impact domain", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ], [ "Open-weights / fine-tuning", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (80)", "+0.6" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Automated CI workflow", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Live web deployment", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 66, "is_new": true, "commits_delta": 80, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "MarinaBeguin/PIVOT", "html_url": "https://github.com/MarinaBeguin/PIVOT", "track": "Build for Your World", "domain": "Multimodal Vision & Video (SAM / Vision)", "summary": "Film a room to get verified 3D answers on whether furniture fits and moves", "readme_summary": "Rebuilds room in 3D, segments objects with SAM 3.1, then Muse/Llama agent calls geometric tools for collisions and paths. Python + Docker with Modal demo. Claims zero false geometry vs 15/36 for Muse alone.", "tech_highlights": [ "SAM 3.1 Vision", "Muse Agent", "Verified 3D Geometry" ], "created_at": "2026-10-27T10:24:01Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 76, "commits_before_window": 0, "prs_total": 17, "prs_merged": 17, "is_preexisting": false, "has_docker": true, "has_tests": true, "has_src": true, "has_ci": true, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": true, "live_urls": [ "https://marina-beguin--pivot-demo-web.modal.run" ], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.2, "score_meta_tooling": 1.8, "score_tech_depth": 1.9, "score_demo": 1.4, "score_total": 7.3, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Docker packaging", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (76)", "+0.6" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Automated CI workflow", "+0.2" ], [ "PR review workflow (17 PRs)", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Live web deployment", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 67, "is_new": true, "commits_delta": 76, "rank_delta": 0, "commits_delta_last_run": 7 }, { "full_name": "zoukmar/burotu", "html_url": "https://github.com/zoukmar/burotu", "track": "Build for Your World", "domain": "Healthcare, Civic Tech & Sustainability", "summary": "Prototype that screens 50 cancers from one blood draw methylation signal", "readme_summary": "Burotu demo teaches Meta Muse models including Muse Glimmer adapter to read tumor DNA methylation from liquid biopsy. Python stack with Docker, docs and benchmark. Not a medical device, test-mode payments only.", "tech_highlights": [ "Muse Glimmer", "Methylation AI", "Python + Docker" ], "created_at": "2026-10-26T19:56:22Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 72, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": true, "has_tests": true, "has_src": true, "has_ci": true, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": true, "has_eval_benchmarks": true, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 1, "score_impact": 2.6, "score_meta_tooling": 1.8, "score_tech_depth": 1.9, "score_demo": 1.0, "score_total": 7.3, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "High-impact domain", "+0.4" ], [ "Eval & benchmark proof", "+0.3" ], [ "Docker packaging", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "Open-weights / fine-tuning", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (72)", "+0.6" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Agent / eval harness", "+0.2" ], [ "Automated CI workflow", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 68, "is_new": true, "commits_delta": 72, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "fahim-muntasir-niloy/krishibondhu-AI-meta-hackathon", "html_url": "https://github.com/fahim-muntasir-niloy/krishibondhu-AI-meta-hackathon", "track": "Build for Your World", "domain": "Healthcare, Civic Tech & Sustainability", "summary": "Bangla voice and photo crop advisor with treatment plan and follow-up", "readme_summary": "KrishiBondhu diagnoses sick-leaf photos in Bangla by voice or image and provides treatment plans with follow-up. Uses Muse, SAM 3.1 and Meta ASR with LangGraph agent, Next.js 16 and Postgres.", "tech_highlights": [ "Muse + SAM 3.1", "Meta ASR + LangGraph", "Next.js 16" ], "created_at": "2026-10-26T14:12:10Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 55, "commits_before_window": 0, "prs_total": 4, "prs_merged": 4, "is_preexisting": false, "has_docker": true, "has_tests": false, "has_src": true, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": true, "video_urls": [ "https://www.youtube.com/watch?v=23cUn40t4lE", "https://youtu.be/23cUn40t4lE" ], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.3, "score_meta_tooling": 1.3, "score_tech_depth": 1.6, "score_demo": 2.1, "score_total": 7.3, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "High-impact domain", "+0.4" ], [ "Docker packaging", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (55)", "+0.6" ], [ "Modular src/ architecture", "+0.3" ], [ "Agent / eval harness", "+0.2" ], [ "PR review workflow (4 PRs)", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Video walkthrough", "+1.1" ], [ "Reproducible setup guide", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 69, "is_new": true, "commits_delta": 55, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "newmachinesph/hoopscliniq-ai", "html_url": "https://github.com/newmachinesph/hoopscliniq-ai", "track": "Build for Your World", "domain": "Multimodal Vision & Video (SAM / Vision)", "summary": "Tracks basketball film and answers coaching questions with cited video claims", "readme_summary": "FastAPI backend on Modal that ingests phone video of a possession and outputs tracked players plus play names. Proxies to a Next.js frontend with offline fallback. Uses SAM 3.1 for player/ball tracking and Muse Spark for play naming and cited Q&A.", "tech_highlights": [ "SAM 3.1 Tracking", "Muse Spark", "FastAPI + Modal" ], "created_at": "2026-10-27T20:48:43Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 11, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": true, "has_setup_guide": true, "has_video_demo": true, "video_urls": [ "https://commons.wikimedia.org/wiki/File:Boys_Varsity_Basketball_v._Stowe_-_Feb._10,_2025.webm", "https://commons.wikimedia.org/wiki/File:Girls_Varsity_Basketball_v._Lake_Region_-_February_11,_2026.webm" ], "has_live_deploy": true, "live_urls": [ "https://web--demo--mnlqynqt4mjy.code.run", "https://del-rosario-llino-g--hoopscliniq-ai-web.us-east.modal.run" ], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.9, "score_meta_tooling": 1.6, "score_tech_depth": 1.3, "score_demo": 2.5, "score_total": 7.3, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Eval & benchmark proof", "+0.3" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "5+ window commits (11)", "+0.2" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Agent / eval harness", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Video walkthrough", "+1.1" ], [ "Reproducible setup guide", "+0.4" ], [ "Live web deployment", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 70, "is_new": true, "commits_delta": 11, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "Cubiczan/aegis-muse-spark", "html_url": "https://github.com/Cubiczan/aegis-muse-spark", "track": "Push the Frontier", "domain": "Developer Tooling, Infra & Security", "summary": "Three-layer guardrail firewall that filters prompts, tools and model outputs.", "readme_summary": "Aegis enforces policy rules, a safety classifier and a tighten-only LLM judge on every agent prompt, tool call and output. Python service with Vercel dashboard, policy.yaml and hash-chained audit log. Built on Muse Spark muse-spark-1.3 with Llama-Guard style prompts.", "tech_highlights": [ "Muse Spark 1.3", "Policy Firewall", "Tamper-evident Audit" ], "created_at": "2026-10-30T01:44:49Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 8, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": false, "has_video_demo": true, "video_urls": [ "https://youtu.be/amdQdMLI1GE" ], "has_live_deploy": true, "live_urls": [ "https://aegis-muse-spark.vercel.app" ], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.3, "score_meta_tooling": 1.8, "score_tech_depth": 1.1, "score_demo": 2.1, "score_total": 7.3, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "High-impact domain", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ] ], "tech": [ [ "Base", "+0.3" ], [ "5+ window commits (8)", "+0.2" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Video walkthrough", "+1.1" ], [ "Live web deployment", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 71, "is_new": true, "commits_delta": 8, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "sanjeevexe/envoy", "html_url": "https://github.com/sanjeevexe/envoy", "track": "Push the Frontier", "domain": "Autonomous Agents & Workflow Automation", "summary": "Phone agent that operates Android apps and compiles runs into self-healing routines", "readme_summary": "Reads Android screens, taps/types with user approvals, and compiles successful runs into self-repairing routines. Exposed as MCP connector for Muse with memory graph, backend + Android bridge.", "tech_highlights": [ "Muse Models", "MCP Connector", "Android UI Agent" ], "created_at": "2026-10-27T01:48:46Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 465, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": true, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": true, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": true, "live_urls": [ "https://sanjeevexe.github.io/envoy/" ], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.6, "score_meta_tooling": 1.3, "score_tech_depth": 1.9, "score_demo": 1.4, "score_total": 7.2, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "High-impact domain", "+0.4" ], [ "Eval & benchmark proof", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (465)", "+0.6" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Agent / eval harness", "+0.2" ], [ "Automated CI workflow", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Live web deployment", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 72, "is_new": true, "commits_delta": 465, "rank_delta": 0, "commits_delta_last_run": 1 }, { "full_name": "summitsingh/launchcrew", "html_url": "https://github.com/summitsingh/launchcrew", "track": "Build for Your World", "domain": "Business, Sales & Commerce", "summary": "Builds approved launch packs via Scout, Maker and Checker with human review", "readme_summary": "Scout, Maker and Checker agents turn demo facts into exportable launch packs with no auto-posting. Stack is FastAPI, Postgres RDS, Next.js on AWS Fargate. Uses Muse models for copy generation with approvals.", "tech_highlights": [ "Muse Spark", "FastAPI + Next.js", "AWS Fargate + RDS" ], "created_at": "2026-10-27T22:56:26Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 398, "commits_before_window": 0, "prs_total": 2, "prs_merged": 0, "is_preexisting": false, "has_docker": true, "has_tests": true, "has_src": true, "has_ci": true, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": true, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 1, "score_impact": 2.5, "score_meta_tooling": 1.8, "score_tech_depth": 1.9, "score_demo": 1.0, "score_total": 7.2, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Eval & benchmark proof", "+0.3" ], [ "Docker packaging", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (398)", "+0.6" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Agent / eval harness", "+0.2" ], [ "Automated CI workflow", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 73, "is_new": false, "commits_delta": 230, "rank_delta": -57, "commits_delta_last_run": 0 }, { "full_name": "abelxmendoza/RobotForge-Hackathon", "html_url": "https://github.com/abelxmendoza/RobotForge-Hackathon", "track": "Push the Frontier", "domain": "Robotics, IoT & Manufacturing", "summary": "Converts text or photos of robots into validated simulation-ready digital twins", "readme_summary": "RobotForge turns a description, photo or parts list into an engineering spec checked like an engineer would, then drives the twin in Gazebo against ground truth. Web app with Garage workflow, parts catalog and live demo. Uses Muse Spark for spec generation and simulation-based validation.", "tech_highlights": [ "Muse Spark", "Gazebo Simulation", "Digital Twin" ], "created_at": "2026-10-26T17:31:28Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 333, "commits_before_window": 0, "prs_total": 106, "prs_merged": 101, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": true, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": true, "live_urls": [ "https://robot-forge-hackathon.vercel.app", "https://robot-forge-hackathon.vercel.app/demo/", "https://robot-forge.vercel.app" ], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.3, "score_meta_tooling": 1.6, "score_tech_depth": 1.9, "score_demo": 1.4, "score_total": 7.2, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "High-impact domain", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (333)", "+0.6" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Automated CI workflow", "+0.2" ], [ "PR review workflow (101 PRs)", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Live web deployment", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 74, "is_new": false, "commits_delta": 221, "rank_delta": -35, "commits_delta_last_run": 6 }, { "full_name": "buildwithdesi/vibeaudit-2", "html_url": "https://github.com/buildwithdesi/vibeaudit-2", "track": "Push the Frontier", "domain": "Developer Tooling, Infra & Security", "summary": "Security audit for AI-generated code with proof of risk and auto-patch", "readme_summary": "Audits a GitHub URL for vulnerabilities, explains risk in plain language with exact lines. Reasoning layer confirms exploitability then patches on sandbox branch and re-scans. Uses Muse Spark exploitability reasoning with Node CLI.", "tech_highlights": [ "Muse Spark 1.3", "Static Analysis Engine", "Node.js CLI" ], "created_at": "2026-10-27T21:13:30Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 95, "commits_before_window": 0, "prs_total": 3, "prs_merged": 3, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": true, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": true, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.3, "score_meta_tooling": 2.0, "score_tech_depth": 1.9, "score_demo": 1.0, "score_total": 7.2, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "High-impact domain", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ], [ "Open-weights / fine-tuning", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (95)", "+0.6" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Automated CI workflow", "+0.2" ], [ "PR review workflow (3 PRs)", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 75, "is_new": false, "commits_delta": 4, "rank_delta": -48, "commits_delta_last_run": 0 }, { "full_name": "EvilMetaMonkey/doc-meta-hackathon", "html_url": "https://github.com/EvilMetaMonkey/doc-meta-hackathon", "track": "Push the Frontier", "domain": "Developer Tooling, Infra & Security", "summary": "Recovery loop for coding agents that bisects bad turns, proposes parallel fixes, and saves lessons.", "readme_summary": "Doc records agent turns, bisects failures, runs three Muse Code fix attempts in parallel worktrees ranked by Muse Wonder, and stores approved lessons. All restores go through dmc preview-first journaled path, cloned at setup. Powered by six Meta models for indie developer track.", "tech_highlights": [ "Muse Wonder", "Muse Code Agents", "dmc Worktrees" ], "created_at": "2026-10-31T05:10:29Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 93, "commits_before_window": 0, "prs_total": 3, "prs_merged": 3, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": true, "has_ci": true, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": true, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.3, "score_meta_tooling": 2.3, "score_tech_depth": 1.6, "score_demo": 1.0, "score_total": 7.2, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "High-impact domain", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ], [ "Open-weights / fine-tuning", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (93)", "+0.6" ], [ "Modular src/ architecture", "+0.3" ], [ "Automated CI workflow", "+0.2" ], [ "PR review workflow (3 PRs)", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 76, "is_new": true, "commits_delta": 93, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "seegongsik/whatif-camera", "html_url": "https://github.com/seegongsik/whatif-camera", "track": "Build for Your World", "domain": "Multimodal Vision & Video (SAM / Vision)", "summary": "Phone street photo app showing places 5 km ahead mapped by side and distance", "readme_summary": "Takes one street photo and lists places along the next 5 km with distance and side. Web app with Vercel frontend and API backend using Overture Maps. Uses Muse Spark for naming notable places and SAM 3.1 for sign detection.", "tech_highlights": [ "SAM 3.1 Vision", "Muse Spark", "Overture Maps" ], "created_at": "2026-10-26T09:14:17Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 91, "commits_before_window": 0, "prs_total": 33, "prs_merged": 32, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": true, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": true, "live_urls": [ "https://whats-ahead.vercel.app", "https://whats-ahead.vercel.app/?street=fifth-avenue", "https://whats-ahead.vercel.app/?street=hollywood-boulevard", "https://whats-ahead.vercel.app/?street=market-street", "https://whats-ahead.vercel.app/?street=7th-avenue", "https://whats-ahead.vercel.app/?street=michigan-avenue", "https://whats-ahead.vercel.app/?street=oxford-street", "https://whats-ahead.vercel.app/?street=champs-elysees", "https://whats-ahead.vercel.app/?street=ginza", "https://whats-ahead.vercel.app/?street=gangnam-daero", "https://whatif-camera.vercel.app" ], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.8, "score_meta_tooling": 2.3, "score_tech_depth": 1.7, "score_demo": 1.4, "score_total": 7.2, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ], [ "Open-weights / fine-tuning", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (91)", "+0.6" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "PR review workflow (32 PRs)", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Live web deployment", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 77, "is_new": false, "commits_delta": 42, "rank_delta": -57, "commits_delta_last_run": 0 }, { "full_name": "seegongsik/whats-ahead", "html_url": "https://github.com/seegongsik/whats-ahead", "track": "Build for Your World", "domain": "Multimodal Vision & Video (SAM / Vision)", "summary": "Phone street photo app showing places 5 km ahead mapped by side and distance", "readme_summary": "Takes one street photo and lists places along the next 5 km with distance and side. Web app with Vercel frontend and API backend using Overture Maps. Uses Muse Spark for naming notable places and SAM 3.1 for sign detection.", "tech_highlights": [ "SAM 3.1 Vision", "Muse Spark", "Overture Maps" ], "created_at": "2026-10-26T09:14:17Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 91, "commits_before_window": 0, "prs_total": 33, "prs_merged": 32, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": true, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": true, "live_urls": [ "https://whats-ahead.vercel.app", "https://whats-ahead.vercel.app/?street=fifth-avenue", "https://whats-ahead.vercel.app/?street=hollywood-boulevard", "https://whats-ahead.vercel.app/?street=market-street", "https://whats-ahead.vercel.app/?street=7th-avenue", "https://whats-ahead.vercel.app/?street=michigan-avenue", "https://whats-ahead.vercel.app/?street=oxford-street", "https://whats-ahead.vercel.app/?street=champs-elysees", "https://whats-ahead.vercel.app/?street=ginza", "https://whats-ahead.vercel.app/?street=gangnam-daero", "https://whatif-camera.vercel.app" ], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.8, "score_meta_tooling": 2.3, "score_tech_depth": 1.7, "score_demo": 1.4, "score_total": 7.2, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ], [ "Open-weights / fine-tuning", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (91)", "+0.6" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "PR review workflow (32 PRs)", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Live web deployment", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 78, "is_new": true, "commits_delta": 91, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "Raul99Alejandro/coresight", "html_url": "https://github.com/Raul99Alejandro/coresight", "track": "Build for Your World", "domain": "Multimodal Vision & Video (SAM / Vision)", "summary": "Turns core-box photos into structured geotechnical drill logs for review", "readme_summary": "Takes ordinary core-box photos and returns per-interval RQD, recovery, lithology logs. Neurosymbolic pipeline: Meta models perceive and describe, deterministic engine computes traceable measurements. Built with Python, Docker, calibration and row-split vision stages.", "tech_highlights": [ "Muse Vision Models", "Computer Vision Pipeline", "Python + Docker" ], "created_at": "2026-10-26T01:32:59Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 86, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": true, "has_tests": true, "has_src": true, "has_ci": true, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": true, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.2, "score_meta_tooling": 2.3, "score_tech_depth": 1.7, "score_demo": 1.0, "score_total": 7.2, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Docker packaging", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ], [ "Open-weights / fine-tuning", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (86)", "+0.6" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Automated CI workflow", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 79, "is_new": false, "commits_delta": 6, "rank_delta": -60, "commits_delta_last_run": 0 }, { "full_name": "ROHITCRAFTSYT/readback", "html_url": "https://github.com/ROHITCRAFTSYT/readback", "track": "Build for Your World", "domain": "Voice, Speech & Audio AI", "summary": "Monitors ATC radio and ADS-B tracks to flag pilot readback mismatches", "readme_summary": "Python service that extracts ATC clearances, checks pilot readbacks, then validates against ADS-B tracks. Runs live, on recorder uploads via review console, or simulated traffic. Uses Meta Muse models for transcription and clearance reasoning.", "tech_highlights": [ "Muse Models", "ADS-B + Audio Pipeline", "Python + Docker" ], "created_at": "2026-10-27T05:06:16Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 68, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": true, "has_tests": true, "has_src": true, "has_ci": true, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": true, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.2, "score_meta_tooling": 2.3, "score_tech_depth": 1.7, "score_demo": 1.0, "score_total": 7.2, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Docker packaging", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ], [ "Open-weights / fine-tuning", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (68)", "+0.6" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Automated CI workflow", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 80, "is_new": false, "commits_delta": 31, "rank_delta": -65, "commits_delta_last_run": 0 }, { "full_name": "pablopriefert/gilmend", "html_url": "https://github.com/pablopriefert/gilmend", "track": "Build for Your World", "domain": "Business, Sales & Commerce", "summary": "Agent that turns damaged parcel photos into carrier claims", "readme_summary": "Customer reports damage with photo, agent finds order and decides reship or refund. Builds carrier claim PDF and email plus customer draft. Uses Muse Spark 1.3, SAM 3.1 and Muse Voice Transcribe.", "tech_highlights": [ "Muse Spark 1.3", "SAM 3.1 Vision", "Next.js + Voice" ], "created_at": "2026-10-27T16:46:07Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 64, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": false, "meta_api_verified": true, "partner_infra": "Baseten", "open_weights_tuning": true, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": true, "live_urls": [ "https://gilmend.vercel.app", "https://damage-desk-ten.vercel.app" ], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.8, "score_meta_tooling": 2.5, "score_tech_depth": 1.5, "score_demo": 1.4, "score_total": 7.2, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ], [ "Partner inference infra", "+0.2" ], [ "Open-weights / fine-tuning", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (64)", "+0.6" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Live web deployment", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 81, "is_new": false, "commits_delta": 0, "rank_delta": -74, "commits_delta_last_run": 0 }, { "full_name": "Ekos-Cyber-Labs/Project-Corvus", "html_url": "https://github.com/Ekos-Cyber-Labs/Project-Corvus", "track": "Push the Frontier", "domain": "Developer Tooling, Infra & Security", "summary": "On-prem SOC analyst that correlates Wazuh alerts into explained MITRE attack chains", "readme_summary": "Corvus plugs into Wazuh via SiemAdapter, normalizes to OCSF and correlates alerts into MITRE ATT&CK incidents. Dockerized Python stack. Uses local Muse Glimmer for triage and Muse Spark over pseudonymized incidents; raw logs stay on-prem.", "tech_highlights": [ "Muse Glimmer", "Muse Spark", "Wazuh + OCSF + Docker" ], "created_at": "2026-10-27T03:46:27Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 59, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": true, "has_tests": true, "has_src": true, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": true, "has_eval_benchmarks": true, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 3.0, "score_meta_tooling": 1.5, "score_tech_depth": 1.7, "score_demo": 1.0, "score_total": 7.2, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "High-impact domain", "+0.4" ], [ "Eval & benchmark proof", "+0.3" ], [ "Docker packaging", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ], [ "Open-weights / fine-tuning", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (59)", "+0.6" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Agent / eval harness", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 82, "is_new": false, "commits_delta": 28, "rank_delta": 49, "commits_delta_last_run": 0 }, { "full_name": "Peakqi-com/panshop", "html_url": "https://github.com/Peakqi-com/panshop", "track": "Build for Your World", "domain": "Business, Sales & Commerce", "summary": "Turns one phone pan into a store with listings, images and videos", "readme_summary": "Converts 1-3 min product pan video into deduplicated catalog, clean images, titles, Meta-ready catalog file and vertical clips. Next.js app by PEAKQI with docs and evals, voice narration captures names/prices. Uses SAM 3.1 and Muse models for detection and copywriting.", "tech_highlights": [ "SAM 3.1 Vision", "Muse Models", "Next.js Commerce" ], "created_at": "2026-11-01T05:22:44Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 35, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": true, "has_ci": true, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": true, "has_eval_benchmarks": true, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": true, "live_urls": [ "https://panshop-henna.vercel.app" ], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.1, "score_meta_tooling": 2.3, "score_tech_depth": 1.4, "score_demo": 1.4, "score_total": 7.2, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Eval & benchmark proof", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ], [ "Open-weights / fine-tuning", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (35)", "+0.4" ], [ "Modular src/ architecture", "+0.3" ], [ "Agent / eval harness", "+0.2" ], [ "Automated CI workflow", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Live web deployment", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 83, "is_new": true, "commits_delta": 35, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "satojandro/meta-hackathon", "html_url": "https://github.com/satojandro/meta-hackathon", "track": "Push the Frontier", "domain": "Developer Tooling, Infra & Security", "summary": "Neuron atlas mapping Muse Glimmer identity neurons into tunable persona dials", "readme_summary": "Exploratory project that probes Muse Glimmer 30B open weights to find persona-related neurons. Python with PyTorch MPS/CUDA, uv, and scripted evals. Uses Muse Spark agent for analysis and a mixer UI instead of prompting.", "tech_highlights": [ "Muse Glimmer 30B", "Muse Spark Agent", "PyTorch MPS/CUDA" ], "created_at": "2026-10-30T02:12:39Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 28, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": true, "has_eval_benchmarks": true, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.6, "score_meta_tooling": 2.1, "score_tech_depth": 1.5, "score_demo": 1.0, "score_total": 7.2, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "High-impact domain", "+0.4" ], [ "Eval & benchmark proof", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "Open-weights / fine-tuning", "+0.5" ], [ "Published HF Hub weights", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (28)", "+0.4" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Agent / eval harness", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 84, "is_new": true, "commits_delta": 28, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "vijayam1/mythree", "html_url": "https://github.com/vijayam1/mythree", "track": "Build for Your World", "domain": "Voice, Speech & Audio AI", "summary": "Video calls that translate 102 languages while preserving own voice", "readme_summary": "Family video calling app where Telugu grandfather and English grandson each hear the other in original voice. Built with Modal deployment, phone join codes, Try page for 102 languages including 22 Indian languages.", "tech_highlights": [ "Voice Cloning", "102 Languages STT/TTS", "Modal + Docker" ], "created_at": "2026-10-27T17:19:01Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 18, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": true, "has_tests": true, "has_src": true, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": true, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": true, "live_urls": [ "https://vijaya-meda--mythree-web.us-east.modal.run/phone", "https://vijaya-meda--mythree-web.us-east.modal.run/try" ], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.2, "score_meta_tooling": 2.3, "score_tech_depth": 1.3, "score_demo": 1.4, "score_total": 7.2, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Docker packaging", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ], [ "Open-weights / fine-tuning", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (18)", "+0.4" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Live web deployment", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 85, "is_new": false, "commits_delta": 13, "rank_delta": 115, "commits_delta_last_run": 0 }, { "full_name": "bhoot-biswas/listsnap", "html_url": "https://github.com/bhoot-biswas/listsnap", "track": "Build for Your World", "domain": "Business, Sales & Commerce", "summary": "Snaps a product photo into a WooCommerce draft in English and Bangla", "readme_summary": "ListSnap is for Bangladesh social-commerce sellers, turning one photo into listing copy, cutout, studio photos and Instagram post. App shell with sign-in, workspaces and stepwise pipeline running on mocks with live Meta models next. Planned stack is Muse Spark, SAM 3.1 and Muse Image plus WooCommerce/Shopify.", "tech_highlights": [ "SAM 3.1 Vision", "Muse Spark 1.3", "Muse Image" ], "created_at": "2026-10-27T06:49:06Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 249, "commits_before_window": 0, "prs_total": 91, "prs_merged": 89, "is_preexisting": false, "has_docker": true, "has_tests": true, "has_src": true, "has_ci": true, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": true, "has_eval_benchmarks": true, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.5, "score_meta_tooling": 1.8, "score_tech_depth": 2.0, "score_demo": 0.8, "score_total": 7.1, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Eval & benchmark proof", "+0.3" ], [ "Docker packaging", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ], [ "Open-weights / fine-tuning", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (249)", "+0.6" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Agent / eval harness", "+0.2" ], [ "Automated CI workflow", "+0.2" ], [ "PR review workflow (89 PRs)", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ] ] }, "rank": 86, "is_new": true, "commits_delta": 249, "rank_delta": 0, "commits_delta_last_run": 12 }, { "full_name": "Dongckim/Meta-Global-AI-Developer-Hackathon", "html_url": "https://github.com/Dongckim/Meta-Global-AI-Developer-Hackathon", "track": "Push the Frontier", "domain": "Robotics, IoT & Manufacturing", "summary": "Glasses assistant that turns lab work into robot protocols hands-free", "readme_summary": "Glassistant connects Ray-Ban Meta glasses to iOS and server for lab tracking and protocol generation. Uses Muse Spark 1.3, Muse Glimmer 30B, SAM 3.1 and Wearables DAT with shared schemas and evals.", "tech_highlights": [ "SAM 3.1 Vision", "Muse Spark 1.3", "Ray-Ban Meta + iOS" ], "created_at": "2026-10-26T22:15:37Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 220, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": true, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": true, "has_eval_benchmarks": true, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.6, "score_meta_tooling": 2.3, "score_tech_depth": 1.4, "score_demo": 0.8, "score_total": 7.1, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "High-impact domain", "+0.4" ], [ "Eval & benchmark proof", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ], [ "Open-weights / fine-tuning", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (220)", "+0.6" ], [ "Modular src/ architecture", "+0.3" ], [ "Agent / eval harness", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ] ] }, "rank": 87, "is_new": false, "commits_delta": 158, "rank_delta": 171, "commits_delta_last_run": 0 }, { "full_name": "EdwinSotto123/blindaje", "html_url": "https://github.com/EdwinSotto123/blindaje", "track": "Build for Your World", "domain": "Healthcare, Civic Tech & Sustainability", "summary": "Disguised notebook app linking extortion evidence across cases in Peru", "readme_summary": "Blindaje keeps victims' WhatsApp voice, photos and messages in an app disguised as a business notebook, transcribes them and links same voice, account or script across cases with human review. Only district-level maps are public. Built with landing, business portal and review console on Workers.", "tech_highlights": [ "Speech Transcription", "Muse Models", "Cloudflare Workers" ], "created_at": "2026-10-28T05:57:22Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 187, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": true, "has_ci": true, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": true, "has_eval_benchmarks": true, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": true, "live_urls": [ "https://blindaje-landing.vigiaperu.workers.dev", "https://blindaje-negocios.vigiaperu.workers.dev", "https://blindaje-console.vigiaperu.workers.dev", "https://blindaje-api.vigiaperu.workers.dev/v1/health" ], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.2, "score_meta_tooling": 2.3, "score_tech_depth": 1.6, "score_demo": 1.0, "score_total": 7.1, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "High-impact domain", "+0.4" ], [ "Eval & benchmark proof", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ], [ "Open-weights / fine-tuning", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (187)", "+0.6" ], [ "Modular src/ architecture", "+0.3" ], [ "Agent / eval harness", "+0.2" ], [ "Automated CI workflow", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Live web deployment", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 88, "is_new": false, "commits_delta": 33, "rank_delta": 212, "commits_delta_last_run": 2 }, { "full_name": "EtkinD/evidomo", "html_url": "https://github.com/EtkinD/evidomo", "track": "Build for Your World", "domain": "Business, Sales & Commerce", "summary": "Verified real-estate listing packs where every claim links to photo or audio proof.", "readme_summary": "Evidomo turns agent photos and voice walkthroughs into publication-ready packs with code-enforced sourcing. Monorepo with web app, Docker Compose and human review gates. Uses Muse Spark for transcription, claim extraction and multilingual packs.", "tech_highlights": [ "Muse Spark 1.3", "Next.js Monorepo", "Evidence-Grounded AI" ], "created_at": "2026-10-28T00:22:50Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 182, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": true, "has_tests": true, "has_src": true, "has_ci": true, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": true, "live_urls": [ "https://evidomo.com" ], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 1, "score_impact": 2.2, "score_meta_tooling": 1.8, "score_tech_depth": 1.7, "score_demo": 1.4, "score_total": 7.1, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Docker packaging", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (182)", "+0.6" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Automated CI workflow", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Live web deployment", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 89, "is_new": false, "commits_delta": 134, "rank_delta": 53, "commits_delta_last_run": 0 }, { "full_name": "aobasar/meta", "html_url": "https://github.com/aobasar/meta", "track": "Build for Your World", "domain": "Multimodal Vision & Video (SAM / Vision)", "summary": "iPhone AR app that labels appliance controls and checks each step visually", "readme_summary": "Kokobubu points iPhone camera at appliances, reads labels, overlays AR markers and guides step-by-step with voice. Verifies completion via camera where visible. iOS app plus web prototype and scripts, using Meta AI vision and language models.", "tech_highlights": [ "Vision + AR Overlay", "Voice Guidance", "iOS + Web Prototype" ], "created_at": "2026-10-27T09:43:52Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 111, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": true, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": true, "video_urls": [ "https://www.youtube.com/watch?v=xyJxzW4g8xU" ], "has_live_deploy": true, "live_urls": [ "https://www.aobasar.com/projects/kokobubu/" ], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.6, "score_meta_tooling": 1.8, "score_tech_depth": 1.2, "score_demo": 2.5, "score_total": 7.1, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (111)", "+0.6" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Video walkthrough", "+1.1" ], [ "Reproducible setup guide", "+0.4" ], [ "Live web deployment", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 90, "is_new": false, "commits_delta": 109, "rank_delta": 380, "commits_delta_last_run": 0 }, { "full_name": "starsmash29/fr-os-ai-perimeter", "html_url": "https://github.com/starsmash29/fr-os-ai-perimeter", "track": "Push the Frontier", "domain": "Developer Tooling, Infra & Security", "summary": "Natural-language firewall changes as approved config patches", "readme_summary": "Sidecar to FR_OS firewall/router OS translates NL requests to validated nftables/eBPF patches. Requires admin approval and adds local human-readable anomaly explanations.", "tech_highlights": [ "nftables + eBPF/XDP", "NL to Config Patch", "Local Anomaly Explainer" ], "created_at": "2026-10-27T05:03:39Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 97, "commits_before_window": 0, "prs_total": 40, "prs_merged": 38, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": true, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": true, "has_eval_benchmarks": false, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.3, "score_meta_tooling": 2.3, "score_tech_depth": 1.9, "score_demo": 0.6, "score_total": 7.1, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "High-impact domain", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ], [ "Open-weights / fine-tuning", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (97)", "+0.6" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Automated CI workflow", "+0.2" ], [ "PR review workflow (38 PRs)", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 91, "is_new": false, "commits_delta": 4, "rank_delta": -78, "commits_delta_last_run": 0 }, { "full_name": "zenbanez/ens-trivial-pass", "html_url": "https://github.com/zenbanez/ens-trivial-pass", "track": "Build for Your World", "domain": "Education & Knowledge Systems", "summary": "Teacher debrief tool that validates classroom notes before creating records", "readme_summary": "Synthetic-only slice of Educational Navigation System for post-class debriefs. Teacher observations become quoted sightings checked by code and gated Nine Gates flow into contestable Digital Twin. Research demo with Firebase hosting.", "tech_highlights": [ "Digital Twin", "Firebase Hosting", "Muse Models" ], "created_at": "2026-10-28T01:50:15Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 69, "commits_before_window": 0, "prs_total": 16, "prs_merged": 16, "is_preexisting": false, "has_docker": true, "has_tests": true, "has_src": false, "has_ci": true, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": true, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.2, "score_meta_tooling": 2.3, "score_tech_depth": 1.6, "score_demo": 1.0, "score_total": 7.1, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Docker packaging", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ], [ "Open-weights / fine-tuning", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (69)", "+0.6" ], [ "Automated test suite", "+0.3" ], [ "Automated CI workflow", "+0.2" ], [ "PR review workflow (16 PRs)", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 92, "is_new": false, "commits_delta": 45, "rank_delta": 228, "commits_delta_last_run": 0 }, { "full_name": "euphoriawolf/forewarn", "html_url": "https://github.com/euphoriawolf/forewarn", "track": "Build for Your World", "domain": "Healthcare, Civic Tech & Sustainability", "summary": "Street-level flood risk forecasts for Africa up to 14 days ahead", "readme_summary": "Agent answers will it flood here with green-amber-red level and actions. Uses 51 rain forecasts plus ground wetness data. Built with Muse Spark Open and Muse Voice Transcribe in English, French, Swahili.", "tech_highlights": [ "Muse Spark Open", "Muse Voice Transcribe", "Rain Forecast Agent" ], "created_at": "2026-10-29T07:08:58Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 65, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": true, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": true, "has_eval_benchmarks": true, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": true, "live_urls": [ "https://forewarn.dawnstackai.com", "https://developers.cloudflare.com/agents/" ], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.0, "score_meta_tooling": 2.3, "score_tech_depth": 1.4, "score_demo": 1.4, "score_total": 7.1, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "High-impact domain", "+0.4" ], [ "Eval & benchmark proof", "+0.3" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ], [ "Open-weights / fine-tuning", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (65)", "+0.6" ], [ "Modular src/ architecture", "+0.3" ], [ "Agent / eval harness", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Live web deployment", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 93, "is_new": false, "commits_delta": 3, "rank_delta": 22, "commits_delta_last_run": 0 }, { "full_name": "TheoEwzZer/ripe", "html_url": "https://github.com/TheoEwzZer/ripe", "track": "Build for Your World", "domain": "Multimodal Vision & Video (SAM / Vision)", "summary": "Snaps fridge photo to map freshness and plan meals first", "readme_summary": "Turns one fridge photo into ingredient freshness map and prioritizes recipes for food about to spoil. Live Next.js + Convex app built on Meta models for Build for Your World, with English/French UI.", "tech_highlights": [ "Meta Vision Models", "Next.js + Convex", "Freshness Mapping" ], "created_at": "2026-10-26T22:12:22Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 47, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": true, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": true, "video_urls": [ "https://youtu.be/5hRNkfudT1s" ], "has_live_deploy": true, "live_urls": [ "https://ripe-six.vercel.app" ], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.8, "score_meta_tooling": 1.8, "score_tech_depth": 1.0, "score_demo": 2.5, "score_total": 7.1, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (47)", "+0.4" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Video walkthrough", "+1.1" ], [ "Reproducible setup guide", "+0.4" ], [ "Live web deployment", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 94, "is_new": true, "commits_delta": 47, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "BlueDocX/agora-rs", "html_url": "https://github.com/BlueDocX/agora-rs", "track": "Push the Frontier", "domain": "Developer Tooling, Infra & Security", "summary": "Rust office where agent claims are checked against signed ledger", "readme_summary": "Agora intercepts agent actions and answers, verifying each claim against a signed append-only ledger before delivery. Built in Rust 2024 with Muse models, includes benchmarks and Cloud Run deployment.", "tech_highlights": [ "Rust 2024", "Muse Models", "Signed Ledger" ], "created_at": "2026-11-01T09:56:23Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 43, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": true, "has_tests": false, "has_src": false, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": true, "has_eval_benchmarks": true, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": true, "live_urls": [ "https://agora-office-295478535981.us-central1.run.app" ], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 1, "score_impact": 3.0, "score_meta_tooling": 1.8, "score_tech_depth": 0.9, "score_demo": 1.4, "score_total": 7.1, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "High-impact domain", "+0.4" ], [ "Eval & benchmark proof", "+0.3" ], [ "Docker packaging", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ], [ "Open-weights / fine-tuning", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (43)", "+0.4" ], [ "Agent / eval harness", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Live web deployment", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 95, "is_new": true, "commits_delta": 43, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "jd-chiles/meta-inspector", "html_url": "https://github.com/jd-chiles/meta-inspector", "track": "Build for Your World", "domain": "Healthcare, Civic Tech & Sustainability", "summary": "Mobile walkthrough guide that stages room videos for habitability inspection forms", "readme_summary": "Mobile-first companion for housing navigators capturing kitchen, bath, bedroom and hallway videos. Separates visual model suggestions from evaluator decisions and stages LAHSA Form 1083 PDF locally. No HMIS submission, demo pseudonymized.", "tech_highlights": [ "Vision inspection aid", "Mobile + Docker", "PDF workflow staging" ], "created_at": "2026-10-27T01:19:41Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 32, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": true, "has_tests": true, "has_src": true, "has_ci": true, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": true, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.6, "score_meta_tooling": 1.8, "score_tech_depth": 1.7, "score_demo": 1.0, "score_total": 7.1, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "High-impact domain", "+0.4" ], [ "Eval & benchmark proof", "+0.3" ], [ "Docker packaging", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (32)", "+0.4" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Agent / eval harness", "+0.2" ], [ "Automated CI workflow", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 96, "is_new": false, "commits_delta": 23, "rank_delta": 148, "commits_delta_last_run": 0 }, { "full_name": "Neufal777/norba-travels-agent", "html_url": "https://github.com/Neufal777/norba-travels-agent", "track": "Build for Your World", "domain": "Autonomous Agents & Workflow Automation", "summary": "AI travel agent that plans trips and books real flights via Norba API.", "readme_summary": "Next.js travel assistant built on Meta models for pre-trip, in-trip and post-trip help. Integrates Norba API over HTTPS for real flight booking plus vision, voice and MCP tools. Includes agency desk and checkout links.", "tech_highlights": [ "Muse Models", "Next.js + MCP", "Voice + Vision" ], "created_at": "2026-10-31T06:38:00Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 32, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": true, "has_tests": false, "has_src": true, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": true, "video_urls": [ "https://youtu.be/aB1zQSqTdUs" ], "has_live_deploy": true, "live_urls": [ "https://agent.norba.io/" ], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.3, "score_meta_tooling": 1.3, "score_tech_depth": 1.0, "score_demo": 2.5, "score_total": 7.1, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "High-impact domain", "+0.4" ], [ "Docker packaging", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (32)", "+0.4" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Video walkthrough", "+1.1" ], [ "Reproducible setup guide", "+0.4" ], [ "Live web deployment", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 97, "is_new": true, "commits_delta": 32, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "devDonald/agripulse-edge", "html_url": "https://github.com/devDonald/agripulse-edge", "track": "Build for Your World", "domain": "Healthcare, Civic Tech & Sustainability", "summary": "Offline-first crop disease diagnosis and voice advice for smallholder farmers", "readme_summary": "Offline-first field client queues photos offline then syncs for diagnosis. Backend uses Meta Model API with Muse Spark/Wonder and SAM 3.1 plus WhatsApp Business API for multilingual voice. Includes ExecuTorch Llama 3.2 benchmark harness for edge fallback.", "tech_highlights": [ "Muse Spark + SAM 3.1", "ExecuTorch Llama 3.2", "WhatsApp + Expo" ], "created_at": "2026-10-26T20:40:32Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 28, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": true, "has_tests": true, "has_src": true, "has_ci": true, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": true, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.6, "score_meta_tooling": 1.8, "score_tech_depth": 1.7, "score_demo": 1.0, "score_total": 7.1, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "High-impact domain", "+0.4" ], [ "Eval & benchmark proof", "+0.3" ], [ "Docker packaging", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (28)", "+0.4" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Agent / eval harness", "+0.2" ], [ "Automated CI workflow", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 98, "is_new": true, "commits_delta": 28, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "ybedoyab/drafty-meta", "html_url": "https://github.com/ybedoyab/drafty-meta", "track": "Build for Your World", "domain": "Robotics, IoT & Manufacturing", "summary": "Parametric CAD workstation that builds solids and runs static stress analysis", "readme_summary": "Engineering workstation where dimensions, material and load generate CadQuery solids meshed by Gmsh and solved by CalculiX. Stack is React 3D view plus FastAPI returning displacements/stresses. Optional Meta model API for natural-language design, Supabase Auth and Modal Cloud.", "tech_highlights": [ "CadQuery + CalculiX", "FastAPI + React 3D", "Gmsh Meshing" ], "created_at": "2026-10-28T05:11:34Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 26, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": true, "has_tests": true, "has_src": true, "has_ci": true, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": true, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.6, "score_meta_tooling": 1.8, "score_tech_depth": 1.7, "score_demo": 1.0, "score_total": 7.1, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "High-impact domain", "+0.4" ], [ "Eval & benchmark proof", "+0.3" ], [ "Docker packaging", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (26)", "+0.4" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Agent / eval harness", "+0.2" ], [ "Automated CI workflow", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 99, "is_new": false, "commits_delta": 0, "rank_delta": -57, "commits_delta_last_run": 0 }, { "full_name": "deaabie/agentpay", "html_url": "https://github.com/deaabie/agentpay", "track": "Push the Frontier", "domain": "Finance, Crypto & Web3", "summary": "Delegates agent spending caps with guardrails and PayPal sandbox settlement", "readme_summary": "AgentPay lets Muse Spark deliberate quota purchases under code guardrails, settles via PayPal Vault Sandbox, and issues visual receipts via Muse Image. Cloudflare Workers with spend ledger and replay.", "tech_highlights": [ "Muse Spark", "PayPal Vault Sandbox", "Muse Image Receipts" ], "created_at": "2026-10-28T06:22:11Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 25, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": true, "video_urls": [ "https://youtu.be/rrnYDFZGDKs" ], "has_live_deploy": true, "live_urls": [ "https://agentpay.skuuy.com" ], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.0, "score_meta_tooling": 1.3, "score_tech_depth": 1.3, "score_demo": 2.5, "score_total": 7.1, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "Domain alignment", "+0.3" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (25)", "+0.4" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Video walkthrough", "+1.1" ], [ "Reproducible setup guide", "+0.4" ], [ "Live web deployment", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 100, "is_new": true, "commits_delta": 25, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "newmachinesph/hoopscliniq-demo", "html_url": "https://github.com/newmachinesph/hoopscliniq-demo", "track": "Build for Your World", "domain": "Multimodal Vision & Video (SAM / Vision)", "summary": "Phone basketball video turned into tagged plays with citations", "readme_summary": "Next.js web app proxying to FastAPI backend hoopscliniq-ai. Core loop Record Tag Ask Study with consent-based player hiding. Uses SAM 3.1 for player detection and Muse models for tagging and Q&A.", "tech_highlights": [ "SAM 3.1 Vision", "Next.js + FastAPI", "Clip-Cited Q&A" ], "created_at": "2026-10-27T19:05:25Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 20, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": true, "has_tests": false, "has_src": true, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": true, "has_setup_guide": true, "has_video_demo": true, "video_urls": [ "https://commons.wikimedia.org/wiki/File:Boys_Varsity_Basketball_v._Stowe_-_Feb._10,_2025.webm", "https://commons.wikimedia.org/wiki/File:Girls_Varsity_Basketball_v._Lake_Region_-_February_11,_2026.webm" ], "has_live_deploy": true, "live_urls": [ "https://web--demo--mnlqynqt4mjy.code.run" ], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.5, "score_meta_tooling": 1.1, "score_tech_depth": 1.2, "score_demo": 2.3, "score_total": 7.1, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Eval & benchmark proof", "+0.3" ], [ "Docker packaging", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (20)", "+0.4" ], [ "Modular src/ architecture", "+0.3" ], [ "Agent / eval harness", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Video walkthrough", "+1.1" ], [ "Reproducible setup guide", "+0.4" ], [ "Live web deployment", "+0.4" ] ] }, "rank": 101, "is_new": true, "commits_delta": 20, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "KingKharid/1Thing-Meta-AI", "html_url": "https://github.com/KingKharid/1Thing-Meta-AI", "track": "Build for Your World", "domain": "General & Emerging Applications", "summary": "Productivity app that hides your task list and shows only one physical next step", "readme_summary": "Takes typed, spoken or photographed chaos, files tasks to hidden reserve, reveals one step at a time. Full-stack with backend, mobile and Modal deployment. Uses Meta AI model to parse input and order next steps.", "tech_highlights": [ "Meta AI", "FastAPI + Next.js", "Modal + Docker" ], "created_at": "2026-10-26T20:39:07Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 14, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": true, "has_tests": true, "has_src": true, "has_ci": true, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": true, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": true, "live_urls": [ "https://kingkharid--1thing-web-web.us-east.modal.run/demo" ], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.1, "score_meta_tooling": 2.3, "score_tech_depth": 1.3, "score_demo": 1.4, "score_total": 7.1, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "General domain", "+0.2" ], [ "Docker packaging", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ], [ "Open-weights / fine-tuning", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "5+ window commits (14)", "+0.2" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Automated CI workflow", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Live web deployment", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 102, "is_new": false, "commits_delta": 10, "rank_delta": 99, "commits_delta_last_run": 4 }, { "full_name": "JeanCyrilleD/nova2-meta-hackathon", "html_url": "https://github.com/JeanCyrilleD/nova2-meta-hackathon", "track": "Build for Your World", "domain": "Healthcare, Civic Tech & Sustainability", "summary": "macOS companion drafting sourced foresight notes, triaging mail and agenda by voice", "readme_summary": "Nova is a native macOS app in Swift with local web UI for humanitarian foresight analysts. It drafts CAFU-format notes with search, files, mail and agenda tools, plus dictation and image generation. All runtime inference uses Meta models including Muse Spark 1.3.", "tech_highlights": [ "Muse Spark 1.3", "Swift + Web UI", "100% Meta Models" ], "created_at": "2026-11-01T10:41:37Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 6, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": false, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": true, "has_setup_guide": true, "has_video_demo": true, "video_urls": [ "https://youtu.be/TSjw5fsBKsM" ], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.2, "score_meta_tooling": 1.8, "score_tech_depth": 1.0, "score_demo": 2.1, "score_total": 7.1, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "High-impact domain", "+0.4" ], [ "Eval & benchmark proof", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ] ], "tech": [ [ "Base", "+0.3" ], [ "5+ window commits (6)", "+0.2" ], [ "Automated test suite", "+0.3" ], [ "Agent / eval harness", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Video walkthrough", "+1.1" ], [ "Reproducible setup guide", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 103, "is_new": true, "commits_delta": 6, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "zaytunazs/accnomos", "html_url": "https://github.com/zaytunazs/accnomos", "track": "Build for Your World", "domain": "Business, Sales & Commerce", "summary": "AI bookkeeping and MTD VAT for UK small firms using files in OneDrive", "readme_summary": "Accnomos does UK small-business bookkeeping with books stored as files in the user's OneDrive. Muse Glimmer 30B / Muse Spark reads receipts with double-checking, user approves to immutable ledger, code computes VAT nine boxes and submits to HMRC sandbox.", "tech_highlights": [ "Muse Glimmer 30B", "OneDrive file ledger", "HMRC sandbox API" ], "created_at": "2026-10-26T22:30:57Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 1504, "commits_before_window": 0, "prs_total": 2, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": true, "has_ci": true, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": true, "has_eval_benchmarks": true, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.1, "score_meta_tooling": 2.3, "score_tech_depth": 1.6, "score_demo": 1.0, "score_total": 7.0, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Eval & benchmark proof", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ], [ "Open-weights / fine-tuning", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (1504)", "+0.6" ], [ "Modular src/ architecture", "+0.3" ], [ "Agent / eval harness", "+0.2" ], [ "Automated CI workflow", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 104, "is_new": false, "commits_delta": 101, "rank_delta": -48, "commits_delta_last_run": 0 }, { "full_name": "vidigoat/wonderland", "html_url": "https://github.com/vidigoat/wonderland", "track": "Build for Your World", "domain": "Education & Knowledge Systems", "summary": "Turns why questions into explorable living worlds grounded in real science", "readme_summary": "Builds interactive simulated worlds from why questions for self-discovery. Uses Muse Spark for reasoning and judging, Muse Image + SAM 3.1 for visuals, Next.js with 40 citizen agents.", "tech_highlights": [ "Muse Spark Open", "Muse Image + SAM 3.1", "Next.js + Vercel" ], "created_at": "2026-10-26T17:22:59Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 369, "commits_before_window": 0, "prs_total": 2, "prs_merged": 2, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": true, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": true, "live_urls": [ "https://wonderland-omega-fawn.vercel.app", "https://wonderland-omega-fawn.vercel.app/teach" ], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.8, "score_meta_tooling": 2.3, "score_tech_depth": 1.5, "score_demo": 1.4, "score_total": 7.0, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ], [ "Open-weights / fine-tuning", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (369)", "+0.6" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Live web deployment", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 105, "is_new": true, "commits_delta": 369, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "xKarimAm/halo", "html_url": "https://github.com/xKarimAm/halo", "track": "Build for Your World", "domain": "Voice, Speech & Audio AI", "summary": "Bilingual Arabic-English Meet copilot showing live points and decisions on video tiles", "readme_summary": "Chrome extension plus Python backend surfaces live points, questions and decisions with quotes and post-call notes. Runs locally with only model calls leaving machine; built on Meta Muse models.", "tech_highlights": [ "Muse Models", "Chrome Ext + Python", "AR Meeting Bubbles" ], "created_at": "2026-10-30T17:07:20Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 181, "commits_before_window": 0, "prs_total": 79, "prs_merged": 75, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": true, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": true, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.8, "score_meta_tooling": 2.3, "score_tech_depth": 1.9, "score_demo": 1.0, "score_total": 7.0, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ], [ "Open-weights / fine-tuning", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (181)", "+0.6" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Automated CI workflow", "+0.2" ], [ "PR review workflow (75 PRs)", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 106, "is_new": true, "commits_delta": 181, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "SebaWag/expediente", "html_url": "https://github.com/SebaWag/expediente", "track": "Build for Your World", "domain": "Legal & Compliance", "summary": "Verifiable procurement dossier engine that footnotes every claim to source page", "readme_summary": "Builds cited investigation dossiers for public procurement where untraceable claims are removed. Python 3.11+ stack with zero dependencies, Docker and CI, plus graph portal and chat UI. Uses Meta AI models for extraction and verification in Startup track Build for Your World.", "tech_highlights": [ "Muse Spark", "Python Zero-Deps", "Graph Portal UI" ], "created_at": "2026-10-27T14:13:52Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 92, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": true, "has_tests": true, "has_src": true, "has_ci": true, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": true, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.5, "score_meta_tooling": 1.6, "score_tech_depth": 1.9, "score_demo": 1.0, "score_total": 7.0, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Eval & benchmark proof", "+0.3" ], [ "Docker packaging", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (92)", "+0.6" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Agent / eval harness", "+0.2" ], [ "Automated CI workflow", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 107, "is_new": false, "commits_delta": 60, "rank_delta": -40, "commits_delta_last_run": 0 }, { "full_name": "thecodekaizen/context", "html_url": "https://github.com/thecodekaizen/context", "track": "Push the Frontier", "domain": "Developer Tooling, Infra & Security", "summary": "Local workstation that reveals what a tech video edit cut out", "readme_summary": "Local video evidence workstation aligning published edits to source with dual-player view. Deterministic 4Hz spatial-color aligner plus timestamped Meta AI interpretation. Dockerized backend traces omissions in tutorials and demos.", "tech_highlights": [ "Video Alignment", "Docker Backend", "Meta AI Analysis" ], "created_at": "2026-10-25T17:42:14Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 59, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": true, "has_docker": true, "has_tests": true, "has_src": true, "has_ci": true, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": true, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 3.0, "score_meta_tooling": 1.1, "score_tech_depth": 1.9, "score_demo": 1.0, "score_total": 7.0, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "High-impact domain", "+0.4" ], [ "Eval & benchmark proof", "+0.3" ], [ "Docker packaging", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (59)", "+0.6" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Agent / eval harness", "+0.2" ], [ "Automated CI workflow", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 108, "is_new": true, "commits_delta": 59, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "JanRaets/global-meta-ai-tempo", "html_url": "https://github.com/JanRaets/global-meta-ai-tempo", "track": "Build for Your World", "domain": "Autonomous Agents & Workflow Automation", "summary": "Calendar agent that computes real departure times and nudges you to leave on time", "readme_summary": ".NET system with Tempo.Api, Core, Agent, Jobs and Web plus Google, Maps, Meta and Push integrations. Learns recurring stops and adjusts plans from chat or invite photos. Uses Meta AI for conversational planning.", "tech_highlights": [ ".NET API + Web", "Maps + Calendar Agent", "Meta Integration" ], "created_at": "2026-10-26T18:42:49Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 56, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": true, "has_tests": true, "has_src": false, "has_ci": true, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": true, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.3, "score_meta_tooling": 2.3, "score_tech_depth": 1.4, "score_demo": 1.0, "score_total": 7.0, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "High-impact domain", "+0.4" ], [ "Docker packaging", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ], [ "Open-weights / fine-tuning", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (56)", "+0.6" ], [ "Automated test suite", "+0.3" ], [ "Automated CI workflow", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 109, "is_new": true, "commits_delta": 56, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "tokyosini573/META-Global-AI-Developer-Hackathon", "html_url": "https://github.com/tokyosini573/META-Global-AI-Developer-Hackathon", "track": "Build for Your World", "domain": "Business, Sales & Commerce", "summary": "Simulates two app launch plans over 90 days in a US market to pick winner", "readme_summary": "Rehearsal is a launch world model that simulates two launch plans for one app over 90 days. Web app on Modal with dual US maps, per-person drawers, and voice/text Q&A. Uses Muse Wonder, Spark, Glimmer and Voice Transcribe for simulation and interviews.", "tech_highlights": [ "Muse Spark 1.3", "Muse Wonder", "Modal + Web" ], "created_at": "2026-10-29T09:40:42Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 42, "commits_before_window": 0, "prs_total": 18, "prs_merged": 18, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": true, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": true, "live_urls": [ "https://tokyosini573--rehearsal.modal.run", "https://tokyosini573--rehearsal.modal.run/?day=90&person=a:87", "https://tokyosini573--rehearsal.modal.run/?new", "https://tokyosini573--rehearsal.modal.run/?backtest" ], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.8, "score_meta_tooling": 2.3, "score_tech_depth": 1.5, "score_demo": 1.4, "score_total": 7.0, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ], [ "Open-weights / fine-tuning", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (42)", "+0.4" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "PR review workflow (18 PRs)", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Live web deployment", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 110, "is_new": true, "commits_delta": 42, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "Dextheking1/by-eye", "html_url": "https://github.com/Dextheking1/by-eye", "track": "Build for Your World", "domain": "Multimodal Vision & Video (SAM / Vision)", "summary": "Turns unmeasured cooking videos into measured recipe cards with evidence", "readme_summary": "Converts phone footage of intuitive cooking into printable recipe cards with estimated amounts and frame evidence. Pipeline samples frames, uses SAM 3.1 for vessel and fill measurement and Muse Spark 1.3 for recipe synthesis, with Muse Voice Transcribe for narration.", "tech_highlights": [ "SAM 3.1 Vision", "Muse Spark 1.3", "Muse Voice Transcribe" ], "created_at": "2026-10-29T01:42:10Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 35, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": true, "video_urls": [ "https://www.youtube.com/watch?v=Amd2NR0n0WQ" ], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.8, "score_meta_tooling": 1.8, "score_tech_depth": 1.3, "score_demo": 2.1, "score_total": 7.0, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (35)", "+0.4" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Video walkthrough", "+1.1" ], [ "Reproducible setup guide", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 111, "is_new": false, "commits_delta": 3, "rank_delta": -103, "commits_delta_last_run": 0 }, { "full_name": "mdmahadyhasanruju-byte/alive-bangladesh-coordinator-meta-ai", "html_url": "https://github.com/mdmahadyhasanruju-byte/alive-bangladesh-coordinator-meta-ai", "track": "Build for Your World", "domain": "Healthcare, Civic Tech & Sustainability", "summary": "Evidence-linked coordinator agent prototype for Bangladesh community help tasks", "readme_summary": "Startup-track coordinator agent proof of meUus Human OS vision with evidence linking. Uses muse-voice-transcribe-1.0 and muse-spark-1.3 for multilingual coordination. Spec-driven docs cover architecture, API contracts, privacy and i18n.", "tech_highlights": [ "Muse Spark 1.3", "Muse Voice Transcribe", "Coordinator Agent" ], "created_at": "2026-10-26T20:50:37Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 19, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": true, "video_urls": [ "https://youtu.be/BvJYe5-Hevo" ], "has_live_deploy": true, "live_urls": [ "https://alive-bangladesh-coordinator-meta-a.vercel.app" ], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.6, "score_meta_tooling": 1.8, "score_tech_depth": 1.3, "score_demo": 2.3, "score_total": 7.0, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "High-impact domain", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (19)", "+0.4" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Video walkthrough", "+1.1" ], [ "Reproducible setup guide", "+0.4" ], [ "Live web deployment", "+0.4" ] ] }, "rank": 112, "is_new": false, "commits_delta": 3, "rank_delta": -109, "commits_delta_last_run": 0 }, { "full_name": "Atikum-AI/latent-judge", "html_url": "https://github.com/Atikum-AI/latent-judge", "track": "Push the Frontier", "domain": "Developer Tooling, Infra & Security", "summary": "Self-evaluating video generation orchestrator that predicts failure and guides retraining", "readme_summary": "Orchestrator agent that classifies, plans, runs, verifies and reports video generations with per-item measurement and evals. Built on Latent Raw format with LTX-2.5 LoRAs and Meterless H-MEM memory. Adds failure prediction and training guidance during hackathon, with SAM 3 planned.", "tech_highlights": [ "Agent Orchestrator", "LTX-2.5 LoRAs", "Evals + H-MEM" ], "created_at": "2026-10-27T11:22:20Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 16, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": true, "has_tests": true, "has_src": false, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": true, "has_eval_benchmarks": true, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.7, "score_meta_tooling": 2.3, "score_tech_depth": 1.2, "score_demo": 0.8, "score_total": 7.0, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "High-impact domain", "+0.4" ], [ "Eval & benchmark proof", "+0.3" ], [ "Docker packaging", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ], [ "Open-weights / fine-tuning", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (16)", "+0.4" ], [ "Automated test suite", "+0.3" ], [ "Agent / eval harness", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ] ] }, "rank": 113, "is_new": false, "commits_delta": 0, "rank_delta": 39, "commits_delta_last_run": 0 }, { "full_name": "KrishVenky/MetaxCerebralValley", "html_url": "https://github.com/KrishVenky/MetaxCerebralValley", "track": "Push the Frontier", "domain": "Autonomous Agents & Workflow Automation", "summary": "Turns scanned P&ID drawings into verified, simulatable connectivity graphs.", "readme_summary": "Agent pipeline that finds symbols with Meta SAM 3.1 over overlapping tiles, builds connectivity and runs deterministic verifier with re-inspection loop. Flags uncertain parts for human review and enables valve isolation simulation.", "tech_highlights": [ "SAM 3.1 Vision", "Verifier Agent Loop", "Python + Simulation" ], "created_at": "2026-10-26T17:41:48Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 10, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": true, "has_eval_benchmarks": true, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.4, "score_meta_tooling": 2.3, "score_tech_depth": 1.3, "score_demo": 1.0, "score_total": 7.0, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "High-impact domain", "+0.4" ], [ "Eval & benchmark proof", "+0.3" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ], [ "Open-weights / fine-tuning", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "5+ window commits (10)", "+0.2" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Agent / eval harness", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 114, "is_new": false, "commits_delta": 6, "rank_delta": 88, "commits_delta_last_run": 0 }, { "full_name": "MatiDegli/oversight", "html_url": "https://github.com/MatiDegli/oversight", "track": "Push the Frontier", "domain": "Developer Tooling, Infra & Security", "summary": "Web IDE to plan, watch and approve multiple coding agents on one repo", "readme_summary": "Oversight lets users supervise coding agents on a live repo graph with git worktrees and impact cones. Built as a Python web IDE with cost and merge controls on Meta Muse Spark. Nothing merges to main without human approval.", "tech_highlights": [ "Muse Spark 1.3", "Python Web IDE", "Git Worktrees" ], "created_at": "2026-10-26T17:25:25Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 1964, "commits_before_window": 0, "prs_total": 414, "prs_merged": 412, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": true, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": true, "live_urls": [ "https://matidegli.github.io/oversight/" ], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.3, "score_meta_tooling": 1.3, "score_tech_depth": 1.9, "score_demo": 1.4, "score_total": 6.9, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "High-impact domain", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (1964)", "+0.6" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Automated CI workflow", "+0.2" ], [ "PR review workflow (412 PRs)", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Live web deployment", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 115, "is_new": true, "commits_delta": 1964, "rank_delta": 0, "commits_delta_last_run": 37 }, { "full_name": "F0rger123/vault-hackathon-2026", "html_url": "https://github.com/F0rger123/vault-hackathon-2026", "track": "Push the Frontier", "domain": "Developer Tooling, Infra & Security", "summary": "Local-first document intelligence that redlines conflicting facts", "readme_summary": "Private Dockerized backend plus CLI that finds conflicts across documents locally. Reads with local Meta Llama 3 for privacy, scoring 10/10 planted conflicts with conflict-redlining pipeline.", "tech_highlights": [ "Meta Llama 3 Local", "Docker Backend + CLI", "Conflict Detection" ], "created_at": "2026-10-26T21:32:09Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 183, "commits_before_window": 0, "prs_total": 50, "prs_merged": 49, "is_preexisting": false, "has_docker": true, "has_tests": true, "has_src": true, "has_ci": true, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 1, "score_impact": 2.7, "score_meta_tooling": 1.3, "score_tech_depth": 1.9, "score_demo": 1.0, "score_total": 6.9, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "High-impact domain", "+0.4" ], [ "Docker packaging", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (183)", "+0.6" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Automated CI workflow", "+0.2" ], [ "PR review workflow (49 PRs)", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 116, "is_new": false, "commits_delta": 87, "rank_delta": -87, "commits_delta_last_run": 0 }, { "full_name": "benoithms/qed-superopt", "html_url": "https://github.com/benoithms/qed-superopt", "track": "Push the Frontier", "domain": "Developer Tooling, Infra & Security", "summary": "LLM superoptimizer for LLVM IR verified correct by Alive2 prover", "readme_summary": "Superoptimizer where Meta models propose faster LLVM IR rewrites beating clang -O3. Alive2 formally proves equivalence for all inputs; counterexamples drive repair loop. Nothing unproven is output.", "tech_highlights": [ "Meta LLM", "Alive2 Prover", "LLVM IR" ], "created_at": "2026-10-26T17:22:14Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 178, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": true, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 1, "score_impact": 2.6, "score_meta_tooling": 1.6, "score_tech_depth": 1.7, "score_demo": 1.0, "score_total": 6.9, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "High-impact domain", "+0.4" ], [ "Eval & benchmark proof", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (178)", "+0.6" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Agent / eval harness", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 117, "is_new": true, "commits_delta": 178, "rank_delta": 0, "commits_delta_last_run": 3 }, { "full_name": "zh315-bit/strollcall", "html_url": "https://github.com/zh315-bit/strollcall", "track": "Build for Your World", "domain": "General & Emerging Applications", "summary": "Plans short NYC walks and fair meetup walks for two people with directions", "readme_summary": "Takes time and vibe prompts to plan walks past nearby places with browser turn-by-turn directions. For pairs, reconciles preferences to find fair walking-time meetup and shared route. Uses Meta models plus deterministic walking-map planner.", "tech_highlights": [ "Meta Muse Models", "Route Planner", "FastAPI + Frontend" ], "created_at": "2026-10-28T18:53:59Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 172, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": true, "has_eval_benchmarks": true, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": true, "live_urls": [ "https://strollcall.onrender.com" ], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.0, "score_meta_tooling": 1.8, "score_tech_depth": 1.7, "score_demo": 1.4, "score_total": 6.9, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "General domain", "+0.2" ], [ "Eval & benchmark proof", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ], [ "Open-weights / fine-tuning", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (172)", "+0.6" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Agent / eval harness", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Live web deployment", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 118, "is_new": false, "commits_delta": 106, "rank_delta": 61, "commits_delta_last_run": 0 }, { "full_name": "nikylogic/ivibe", "html_url": "https://github.com/nikylogic/ivibe", "track": "Push the Frontier", "domain": "Developer Tooling, Infra & Security", "summary": "Captures bug reproductions and generates prompts for fixing them", "readme_summary": "iVibe captures bug demonstrations and converts them into structured prompts for AI coding workflows. Repository includes cross-platform client with architecture docs and CI. Designed to work with Muse models for reproduction-to-prompt generation.", "tech_highlights": [ "Muse Models", "Bug-to-Prompt", "Desktop Client" ], "created_at": "2026-10-27T12:49:34Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 103, "commits_before_window": 0, "prs_total": 1, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": true, "has_ci": true, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": true, "live_urls": [ "https://ivibe.tech" ], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 4, "score_impact": 2.3, "score_meta_tooling": 1.8, "score_tech_depth": 1.4, "score_demo": 1.4, "score_total": 6.9, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "High-impact domain", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (103)", "+0.6" ], [ "Modular src/ architecture", "+0.3" ], [ "Automated CI workflow", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Live web deployment", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 119, "is_new": true, "commits_delta": 103, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "Mishallic/Afterimage", "html_url": "https://github.com/Mishallic/Afterimage", "track": "Build for Your World", "domain": "Multimodal Vision & Video (SAM / Vision)", "summary": "Removes the painter from process footage so brush strokes appear on their own.", "readme_summary": "Afterimage aligns and averages camera frames to erase hands and tools without generative inpainting. Python pipeline with evals and tests, runnable via Meta API or open weights on Modal/Baseten. Uses SAM 3.1 for masking and Muse Spark for orchestration.", "tech_highlights": [ "SAM 3.1 Vision", "Muse Spark", "Modal GPU" ], "created_at": "2026-10-30T08:19:54Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 73, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": true, "has_eval_benchmarks": true, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.9, "score_meta_tooling": 2.3, "score_tech_depth": 1.7, "score_demo": 1.0, "score_total": 6.9, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Eval & benchmark proof", "+0.3" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ], [ "Open-weights / fine-tuning", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (73)", "+0.6" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Agent / eval harness", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 120, "is_new": true, "commits_delta": 73, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "AnnieQian1212/BoardDream", "html_url": "https://github.com/AnnieQian1212/BoardDream", "track": "Build for Your World", "domain": "Gaming, Entertainment & Creative Media", "summary": "Turns one sentence into a coded board game playtested over 1000 simulations", "readme_summary": "Turns a prompt into a strategy game plan, retrieves mechanics, generates rules as code, then simulates 1000 games to fix flaws. TypeScript monorepo with 3D table and retrieval eval harness. Uses Muse Spark for design and code generation.", "tech_highlights": [ "Muse Spark", "Procedural Board Gen", "3D Table + Evals" ], "created_at": "2026-10-26T21:39:58Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 70, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": true, "has_tests": true, "has_src": true, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": true, "has_eval_benchmarks": true, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.4, "score_meta_tooling": 1.8, "score_tech_depth": 1.7, "score_demo": 1.0, "score_total": 6.9, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "General domain", "+0.2" ], [ "Eval & benchmark proof", "+0.3" ], [ "Docker packaging", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ], [ "Open-weights / fine-tuning", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (70)", "+0.6" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Agent / eval harness", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 121, "is_new": false, "commits_delta": 30, "rank_delta": 47, "commits_delta_last_run": 4 }, { "full_name": "jeshwanthsingh/muse-guard", "html_url": "https://github.com/jeshwanthsingh/muse-guard", "track": "Push the Frontier", "domain": "Developer Tooling, Infra & Security", "summary": "Spec clash detector with independent verification of AI code fixes", "readme_summary": "Resolves conflicting requirements by exhaustively finding disagreements, letting user decide winner, then having Meta coding agent implement. Independent checker verifies fix with measured 160-run study. Live Modal web demo.", "tech_highlights": [ "Muse Coding Agent", "Policy Verification", "Modal Live Demo" ], "created_at": "2026-10-26T16:46:45Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 68, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": true, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": true, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": true, "live_urls": [ "https://jeshwanthsingh--muse-guard-live-web.us-east.modal.run/" ], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.3, "score_meta_tooling": 1.5, "score_tech_depth": 1.7, "score_demo": 1.4, "score_total": 6.9, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "High-impact domain", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ], [ "Open-weights / fine-tuning", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (68)", "+0.6" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Automated CI workflow", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Live web deployment", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 122, "is_new": false, "commits_delta": 32, "rank_delta": 38, "commits_delta_last_run": 0 }, { "full_name": "imogikk7/sayso", "html_url": "https://github.com/imogikk7/sayso", "track": "Build for Your World", "domain": "General & Emerging Applications", "summary": "iOS keyboard that rewrites text in your personal style with LoRA voice", "readme_summary": "Learns personal chat, email and essay style per contact with feedback rules and on-device learning. Stack spans iOS keyboard, Back Tap shortcut, chat app, training and serving pipelines. Uses Meta Muse Glimmer with personal LoRA fine-tuning for style rewrite and generation.", "tech_highlights": [ "Muse Glimmer LoRA", "iOS Keyboard App", "Personalization Pipeline" ], "created_at": "2026-10-27T13:29:37Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 67, "commits_before_window": 0, "prs_total": 7, "prs_merged": 7, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": false, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": true, "has_eval_benchmarks": true, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.0, "score_meta_tooling": 2.3, "score_tech_depth": 1.6, "score_demo": 1.0, "score_total": 6.9, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "General domain", "+0.2" ], [ "Eval & benchmark proof", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ], [ "Open-weights / fine-tuning", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (67)", "+0.6" ], [ "Automated test suite", "+0.3" ], [ "Agent / eval harness", "+0.2" ], [ "PR review workflow (7 PRs)", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 123, "is_new": false, "commits_delta": 42, "rank_delta": 273, "commits_delta_last_run": 0 }, { "full_name": "Akhilvallala1/veil", "html_url": "https://github.com/Akhilvallala1/veil", "track": "Push the Frontier", "domain": "Developer Tooling, Infra & Security", "summary": "Privacy firewall that veils screens so cloud agents never see real sensitive values", "readme_summary": "Veil is a privacy firewall for computer-use agents that sends only veiled screens to cloud models with policy enforcement. Python stack with policy, bench and infra. Uses Muse Wonder in cloud, Muse Glimmer and SAM 3.1 locally on raw pixels.", "tech_highlights": [ "Muse Wonder", "Muse Glimmer", "SAM 3.1 Vision" ], "created_at": "2026-10-26T17:14:43Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 48, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": true, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.3, "score_meta_tooling": 2.3, "score_tech_depth": 1.3, "score_demo": 1.0, "score_total": 6.9, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "High-impact domain", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ], [ "Open-weights / fine-tuning", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (48)", "+0.4" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 124, "is_new": false, "commits_delta": 8, "rank_delta": -94, "commits_delta_last_run": 0 }, { "full_name": "gokunguru/netops-copilot", "html_url": "https://github.com/gokunguru/netops-copilot", "track": "Push the Frontier", "domain": "Developer Tooling, Infra & Security", "summary": "Converts plain-language network requests into validated multi-vendor configs with approval", "readme_summary": "AI agent generating validated configs, Ansible playbooks, proven rollback and tamper-evident journal. Deterministic safety gate plus lab dry-run and human approval. Python, Docker, Modal demo, policies and replays, using Muse Spark API.", "tech_highlights": [ "Muse Spark", "Ansible + Dry-Run", "Safety Gate + Journal" ], "created_at": "2026-10-26T08:23:38Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 19, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": true, "has_tests": true, "has_src": true, "has_ci": true, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": true, "live_urls": [ "https://gokunguru--netops-copilot-demo-web.us-east.modal.run" ], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.7, "score_meta_tooling": 1.3, "score_tech_depth": 1.5, "score_demo": 1.4, "score_total": 6.9, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "High-impact domain", "+0.4" ], [ "Docker packaging", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (19)", "+0.4" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Automated CI workflow", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Live web deployment", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 125, "is_new": false, "commits_delta": 14, "rank_delta": 63, "commits_delta_last_run": 3 }, { "full_name": "Chaitya02/dex-ai", "html_url": "https://github.com/Chaitya02/dex-ai", "track": "Build for Your World", "domain": "Finance, Crypto & Web3", "summary": "Voice-first expense splitter that reads group bills and logs shares", "readme_summary": "Dex photographs group receipts, transcribes who-had-what by voice, splits items, and writes to Balance Desk on approval. Python stack with evals and tests. Uses muse-spark-1.3 for receipt vision, voice-transcribe-1.0, and sam-3.1 for receipt detection.", "tech_highlights": [ "Muse Spark 1.3", "SAM 3.1 Vision", "Voice Transcribe AI" ], "created_at": "2026-10-26T17:41:16Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 13, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": true, "has_tests": true, "has_src": true, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": true, "has_eval_benchmarks": true, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.5, "score_meta_tooling": 2.3, "score_tech_depth": 1.3, "score_demo": 0.8, "score_total": 6.9, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Eval & benchmark proof", "+0.3" ], [ "Docker packaging", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ], [ "Open-weights / fine-tuning", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "5+ window commits (13)", "+0.2" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Agent / eval harness", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ] ] }, "rank": 126, "is_new": false, "commits_delta": 4, "rank_delta": 60, "commits_delta_last_run": 2 }, { "full_name": "laxmanshah45/chalk-talk", "html_url": "https://github.com/laxmanshah45/chalk-talk", "track": "Build for Your World", "domain": "Education & Knowledge Systems", "summary": "Animated chalk tutor that narrates lessons and answers speech", "readme_summary": "Interactive tutor that generates chalk-style visuals per lesson scene with synced narration. Built on Meta Model API with SAM 3.1 for textbook photo tracing, Muse Spark for lessons, voice Q&A and tap-to-find quizzes.", "tech_highlights": [ "SAM 3.1 Vision", "Muse Spark 1.3", "Node.js + Canvas" ], "created_at": "2026-10-29T17:24:58Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 13, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": true, "has_tests": false, "has_src": true, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": true, "video_urls": [ "https://youtu.be/hLgwl60q20I" ], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.2, "score_meta_tooling": 1.8, "score_tech_depth": 0.8, "score_demo": 2.1, "score_total": 6.9, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Docker packaging", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ] ], "tech": [ [ "Base", "+0.3" ], [ "5+ window commits (13)", "+0.2" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Video walkthrough", "+1.1" ], [ "Reproducible setup guide", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 127, "is_new": true, "commits_delta": 13, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "tausif2907/Archaeo", "html_url": "https://github.com/tausif2907/Archaeo", "track": "Push the Frontier", "domain": "Developer Tooling, Infra & Security", "summary": "Repo history explorer that maps eras, architecture, and bug causes with citations", "readme_summary": "Archaeo ingests full Git history to build timelines, interactive architecture maps, and why-explanations. Stack uses Docker Compose with frontend and backend apps. Uses Muse models via Meta API for cited code reasoning with commit links.", "tech_highlights": [ "Muse Spark 1.3", "Docker + Monorepo", "Arch Map + Citations" ], "created_at": "2026-10-29T15:15:25Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 9, "commits_before_window": 68, "prs_total": 0, "prs_merged": 0, "is_preexisting": true, "has_docker": true, "has_tests": false, "has_src": true, "has_ci": true, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": true, "has_eval_benchmarks": true, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 3.0, "score_meta_tooling": 2.0, "score_tech_depth": 0.9, "score_demo": 1.0, "score_total": 6.9, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "High-impact domain", "+0.4" ], [ "Eval & benchmark proof", "+0.3" ], [ "Docker packaging", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ], [ "Open-weights / fine-tuning", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "5+ window commits (9)", "+0.2" ], [ "Modular src/ architecture", "+0.3" ], [ "Agent / eval harness", "+0.2" ], [ "Automated CI workflow", "+0.2" ], [ "Pre-Oct 26 commits dominate (68)", "-0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 128, "is_new": true, "commits_delta": 9, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "ArgeTheGamer/PsycheEngine", "html_url": "https://github.com/ArgeTheGamer/PsycheEngine", "track": "Push the Frontier", "domain": "Autonomous Agents & Workflow Automation", "summary": "Multi-agent writer that keeps long company documents mutually consistent", "readme_summary": "Writes warehouse manuals, safety docs and agreements from one shared canon of facts and updates all pages when facts change. Runs on Muse Spark with engine plus web dashboard. Built for Meta hackathon using fictional Harborwick 3PL data.", "tech_highlights": [ "Muse Spark", "Multi-Agent Runtime", "Shared Fact Canon" ], "created_at": "2026-10-26T16:27:56Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 166, "commits_before_window": 0, "prs_total": 24, "prs_merged": 24, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": false, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": true, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": true, "live_urls": [ "https://psycheengine-argethegamers-projects.vercel.app", "https://psycheengine.vercel.app" ], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.3, "score_meta_tooling": 2.0, "score_tech_depth": 1.1, "score_demo": 1.4, "score_total": 6.8, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "High-impact domain", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ], [ "Open-weights / fine-tuning", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (166)", "+0.6" ], [ "PR review workflow (24 PRs)", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Live web deployment", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 129, "is_new": false, "commits_delta": 40, "rank_delta": -1, "commits_delta_last_run": 0 }, { "full_name": "kamil-shirinov/Archivist", "html_url": "https://github.com/kamil-shirinov/Archivist", "track": "Build for Your World", "domain": "Finance, Crypto & Web3", "summary": "Turns scanned financial archives into cited, verified database", "readme_summary": "Digitizes scanned financial archives with citation to page location, arithmetic checks and blind second read. Flags uncertain values for human review, never auto-corrects. Uses four Meta models in pipeline.", "tech_highlights": [ "Meta Models x4", "OCR + Verification", "Python Pipeline" ], "created_at": "2026-10-26T15:43:39Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 138, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": true, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": true, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.8, "score_meta_tooling": 2.3, "score_tech_depth": 1.7, "score_demo": 1.0, "score_total": 6.8, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ], [ "Open-weights / fine-tuning", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (138)", "+0.6" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Automated CI workflow", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 130, "is_new": true, "commits_delta": 138, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "Dominic-Pi-Sunyer/munix", "html_url": "https://github.com/Dominic-Pi-Sunyer/munix", "track": "Push the Frontier", "domain": "Developer Tooling, Infra & Security", "summary": "Agent runtime that blocks prompt injection by gating tool calls in code", "readme_summary": "Rust runtime where agents act only through a Gate checking calls against a pre-signed plan. Provenance tracking denies injected instructions; built on Muse Spark for the hackathon.", "tech_highlights": [ "Muse Spark", "Rust Gate Runtime", "Prompt Injection Defense" ], "created_at": "2026-10-26T16:20:06Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 123, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": true, "has_ci": true, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": true, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.6, "score_meta_tooling": 1.6, "score_tech_depth": 1.6, "score_demo": 1.0, "score_total": 6.8, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "High-impact domain", "+0.4" ], [ "Eval & benchmark proof", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (123)", "+0.6" ], [ "Modular src/ architecture", "+0.3" ], [ "Agent / eval harness", "+0.2" ], [ "Automated CI workflow", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 131, "is_new": false, "commits_delta": 28, "rank_delta": -63, "commits_delta_last_run": 0 }, { "full_name": "dudhasch/contextpane", "html_url": "https://github.com/dudhasch/contextpane", "track": "Push the Frontier", "domain": "Developer Tooling, Infra & Security", "summary": "Local-first workbench that fixes Entra ID, Intune and Azure incidents safely", "readme_summary": "Correlates vague tickets with live tenant state across Entra ID, Intune and Azure ARM. Generates catalog-constrained diagnostic UI via MCP with operator approval. Uses Muse Glimmer 30B, Spark 1.3, Wonder 1.0 and Voice Transcribe in order.", "tech_highlights": [ "Muse Glimmer 30B", "MCP + GenUI", "Bun + Modal L40S" ], "created_at": "2026-10-26T16:52:15Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 117, "commits_before_window": 0, "prs_total": 3, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": true, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": true, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.3, "score_meta_tooling": 2.3, "score_tech_depth": 1.2, "score_demo": 1.0, "score_total": 6.8, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "High-impact domain", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ], [ "Open-weights / fine-tuning", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (117)", "+0.6" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 132, "is_new": false, "commits_delta": 0, "rank_delta": -54, "commits_delta_last_run": 0 }, { "full_name": "Fluffy-SHIBAINU/biscuit", "html_url": "https://github.com/Fluffy-SHIBAINU/biscuit", "track": "Build for Your World", "domain": "Voice, Speech & Audio AI", "summary": "Voice helper on seniors phones that reads mail aloud and quotes only what is on the page.", "readme_summary": "Biscuit watches for mail delivery, chimes, reads letters aloud, asks follow-ups, and starts approval-gated cases. Family page shows transcripts and daughter approval; emergency call to 911 supported. Built as Kindred AI web app with voice interface and quote-grounded responses.", "tech_highlights": [ "Voice-First UI", "Muse Models", "Next.js + Drizzle" ], "created_at": "2026-10-29T03:03:44Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 110, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": true, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": true, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.8, "score_meta_tooling": 2.3, "score_tech_depth": 1.7, "score_demo": 1.0, "score_total": 6.8, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ], [ "Open-weights / fine-tuning", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (110)", "+0.6" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Automated CI workflow", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 133, "is_new": false, "commits_delta": 62, "rank_delta": -64, "commits_delta_last_run": 0 }, { "full_name": "daylorza/cyber-stage", "html_url": "https://github.com/daylorza/cyber-stage", "track": "Build for Your World", "domain": "Business, Sales & Commerce", "summary": "Turns phone walkthrough video into staged broker-approved real estate listing", "readme_summary": "Stages filmed rooms preserving geometry, writes copy from what camera saw, enables broker approval and first-person walkthrough. Built with Muse Spark, Wonder, Image and SAM 3.1.", "tech_highlights": [ "Muse Spark 1.3", "SAM 3.1 + Wonder", "Muse Image" ], "created_at": "2026-10-26T15:24:43Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 106, "commits_before_window": 0, "prs_total": 20, "prs_merged": 17, "is_preexisting": false, "has_docker": true, "has_tests": false, "has_src": true, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": true, "live_urls": [ "https://cyber-stage.fly.dev/" ], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.2, "score_meta_tooling": 1.8, "score_tech_depth": 1.4, "score_demo": 1.4, "score_total": 6.8, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Docker packaging", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (106)", "+0.6" ], [ "Modular src/ architecture", "+0.3" ], [ "PR review workflow (17 PRs)", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Live web deployment", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 134, "is_new": true, "commits_delta": 106, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "hkdebendo/autolab", "html_url": "https://github.com/hkdebendo/autolab", "track": "Push the Frontier", "domain": "Healthcare, Civic Tech & Sustainability", "summary": "Closed-loop AI lab that proposes and simulates cobalt-free battery electrolytes.", "readme_summary": "AutoLab loops hypothesis, crystal building, simulation, filtering, and correction for solid electrolytes. Stack is Python, Modal GPU jobs, notebooks, and web frontend. Uses Muse Spark for proposals and Meta FAIR UMA for materials simulation.", "tech_highlights": [ "Muse Spark", "Meta UMA Simulate", "Modal + Python" ], "created_at": "2026-10-26T14:13:46Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 81, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": true, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.3, "score_meta_tooling": 2.0, "score_tech_depth": 1.5, "score_demo": 1.0, "score_total": 6.8, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "High-impact domain", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ], [ "Open-weights / fine-tuning", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (81)", "+0.6" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 135, "is_new": false, "commits_delta": 28, "rank_delta": 24, "commits_delta_last_run": 0 }, { "full_name": "Clar17y/ChaosPilot", "html_url": "https://github.com/Clar17y/ChaosPilot", "track": "Push the Frontier", "domain": "Developer Tooling, Infra & Security", "summary": "Workbench that proposes and runs failure experiments to verify bugs in event systems", "readme_summary": "Reads source and behavioral contracts to propose chaos experiments and runs them on fresh deterministic instances. Includes synthetic trading and inventory-reservation targets with mocked offline mode. Live investigation requires Meta Model API key.", "tech_highlights": [ "Meta Model API", "Node.js 24", "Deterministic Harness" ], "created_at": "2026-10-26T16:29:11Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 63, "commits_before_window": 0, "prs_total": 21, "prs_merged": 21, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.3, "score_meta_tooling": 1.8, "score_tech_depth": 1.7, "score_demo": 1.0, "score_total": 6.8, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "High-impact domain", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (63)", "+0.6" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "PR review workflow (21 PRs)", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 136, "is_new": true, "commits_delta": 63, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "Vaydelux/TerraResponseAI_Meta_Hackathon_2026", "html_url": "https://github.com/Vaydelux/TerraResponseAI_Meta_Hackathon_2026", "track": "Build for Your World", "domain": "Healthcare, Civic Tech & Sustainability", "summary": "Reviews disaster photos to triage damage for responder teams", "readme_summary": "Authenticated users upload disaster photos validated via magic bytes and Sharp decode. AI generates labeled unverified observations and priority scores for human confirm or reject. Next.js stack with Muse vision models for triage.", "tech_highlights": [ "Muse Vision", "Next.js + Sharp", "Human-in-the-Loop" ], "created_at": "2026-10-28T14:13:32Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 51, "commits_before_window": 0, "prs_total": 28, "prs_merged": 27, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": true, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": true, "live_urls": [ "https://terra-response-ai.vercel.app" ], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.9, "score_meta_tooling": 1.6, "score_tech_depth": 1.9, "score_demo": 1.4, "score_total": 6.8, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "High-impact domain", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (51)", "+0.6" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Automated CI workflow", "+0.2" ], [ "PR review workflow (27 PRs)", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Live web deployment", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 137, "is_new": true, "commits_delta": 51, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "GlamgarOnDiscord/parity-agent", "html_url": "https://github.com/GlamgarOnDiscord/parity-agent", "track": "Push the Frontier", "domain": "Developer Tooling, Infra & Security", "summary": "Records legacy apps and rebuilds them as modern web apps with field-level proof", "readme_summary": "Pipeline of record, explore, rules, rebuild, prove that watches legacy app use under Wine, extracts business rules, generates a web app, then replays scenarios to compare fields. Built with Bun/TypeScript, keeps replay proof for later AI or human changes.", "tech_highlights": [ "Muse Code", "Replay Verification", "Bun + TypeScript" ], "created_at": "2026-10-26T16:32:18Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 46, "commits_before_window": 0, "prs_total": 49, "prs_merged": 45, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": true, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.3, "score_meta_tooling": 1.8, "score_tech_depth": 1.7, "score_demo": 1.0, "score_total": 6.8, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "High-impact domain", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (46)", "+0.4" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Automated CI workflow", "+0.2" ], [ "PR review workflow (45 PRs)", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 138, "is_new": false, "commits_delta": 8, "rank_delta": -85, "commits_delta_last_run": 1 }, { "full_name": "aeroxy/paper-bro", "html_url": "https://github.com/aeroxy/paper-bro", "track": "Build for Your World", "domain": "Education & Knowledge Systems", "summary": "Paste an arXiv link to generate an interactive published course", "readme_summary": "paper-bro turns one arXiv paper into one interactive course hosted on AERO. Rust axum/tokio server with Neon Postgres, React 19 Vite Tailwind SPA, SSE progress. Uses Muse Spark Open via OpenAI-compatible API.", "tech_highlights": [ "Muse Spark Open", "Rust axum + tokio", "React 19 + Vite" ], "created_at": "2015-01-13T15:20:49Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 35, "commits_before_window": 0, "prs_total": 2, "prs_merged": 2, "is_preexisting": true, "has_docker": false, "has_tests": false, "has_src": true, "has_ci": true, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": true, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": true, "video_urls": [ "https://youtube.com/shorts/utHsTx-Orys", "https://www.youtube.com/watch?v=7egZZNXmRTQ", "https://www.youtube.com/watch?v=utHsTx-Orys" ], "has_live_deploy": true, "live_urls": [ "https://aero.oops.wtf/paper-bro" ], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 12, "score_impact": 1.8, "score_meta_tooling": 1.3, "score_tech_depth": 1.2, "score_demo": 2.5, "score_total": 6.8, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "Open-weights / fine-tuning", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (35)", "+0.4" ], [ "Modular src/ architecture", "+0.3" ], [ "Automated CI workflow", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Video walkthrough", "+1.1" ], [ "Reproducible setup guide", "+0.4" ], [ "Live web deployment", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 139, "is_new": true, "commits_delta": 35, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "antonipuszczahub/sparing-live-muse", "html_url": "https://github.com/antonipuszczahub/sparing-live-muse", "track": "Build for Your World", "domain": "Voice, Speech & Audio AI", "summary": "Real-time voice sparring partner with review in English and Polish.", "readme_summary": "Full-duplex voice system for rehearsing difficult conversations with interrupting AI counterparts. Pipeline of specialized agents with hidden state, screen context and reviewer feedback. Built on Meta Muse models with Node server and web client.", "tech_highlights": [ "Muse Voice Loop", "Full-Duplex Audio", "Multi-Agent Review" ], "created_at": "2026-10-27T20:19:49Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 30, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": true, "has_tests": true, "has_src": true, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": true, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.5, "score_meta_tooling": 1.8, "score_tech_depth": 1.5, "score_demo": 1.0, "score_total": 6.8, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Eval & benchmark proof", "+0.3" ], [ "Docker packaging", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (30)", "+0.4" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Agent / eval harness", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 140, "is_new": false, "commits_delta": 0, "rank_delta": -103, "commits_delta_last_run": 0 }, { "full_name": "Acookiefor2/script-or-ai", "html_url": "https://github.com/Acookiefor2/script-or-ai", "track": "Push the Frontier", "domain": "Developer Tooling, Infra & Security", "summary": "Benchmark testing if Muse can tell rule bots from LLMs pretending to be scripts", "readme_summary": "Runs interrogation games where Muse Spark interrogator scores suspicion against real scripts versus AI impersonators. Dashboard replays games with logs and analysis scripts. Built with Muse Spark 1.3 for evaluation research.", "tech_highlights": [ "Muse Spark 1.3", "Trust Benchmark", "Replay Dashboard" ], "created_at": "2026-10-26T16:49:25Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 29, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": true, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": true, "live_urls": [ "https://acookiefor2.github.io/script-or-ai/dashboard/" ], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.6, "score_meta_tooling": 1.3, "score_tech_depth": 1.5, "score_demo": 1.4, "score_total": 6.8, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "High-impact domain", "+0.4" ], [ "Eval & benchmark proof", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (29)", "+0.4" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Agent / eval harness", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Live web deployment", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 141, "is_new": false, "commits_delta": 8, "rank_delta": -8, "commits_delta_last_run": 0 }, { "full_name": "wildanlsfs/traction-radar", "html_url": "https://github.com/wildanlsfs/traction-radar", "track": "Build for Your World", "domain": "Business, Sales & Commerce", "summary": "AI agent finds first users and runs measurable growth tests", "readme_summary": "Docker + Node service with web UI that builds a product card from a URL and web search. Muse Spark identifies audiences and phrases, then plans small experiments and learns from outcomes.", "tech_highlights": [ "Muse Spark", "Node + Docker", "Growth Agent" ], "created_at": "2026-10-29T03:07:05Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 23, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": true, "has_tests": true, "has_src": true, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": true, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.2, "score_meta_tooling": 2.3, "score_tech_depth": 1.3, "score_demo": 1.0, "score_total": 6.8, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Docker packaging", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ], [ "Open-weights / fine-tuning", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (23)", "+0.4" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 142, "is_new": false, "commits_delta": 22, "rank_delta": 64, "commits_delta_last_run": 2 }, { "full_name": "compiler-aditya/groundtruth", "html_url": "https://github.com/compiler-aditya/groundtruth", "track": "Build for Your World", "domain": "Multimodal Vision & Video (SAM / Vision)", "summary": "Checks construction photos against design package with cited evidence", "readme_summary": "Muse Wonder agent maps drone stills and walkthroughs to design items and runs checks with SAM 3.1 and Muse Spark. Live Vercel demo with step-by-step findings, drafts, and evidence browsing.", "tech_highlights": [ "SAM 3.1 Vision", "Muse Wonder Agent", "Muse Spark 1.3" ], "created_at": "2026-10-31T08:21:42Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 20, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": true, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": true, "live_urls": [ "https://groundtruth-mu-gules.vercel.app" ], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.8, "score_meta_tooling": 2.3, "score_tech_depth": 1.3, "score_demo": 1.4, "score_total": 6.8, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ], [ "Open-weights / fine-tuning", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (20)", "+0.4" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Live web deployment", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 143, "is_new": true, "commits_delta": 20, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "daarsai/daars_turnproof", "html_url": "https://github.com/daarsai/daars_turnproof", "track": "Build for Your World", "domain": "Multimodal Vision & Video (SAM / Vision)", "summary": "Verifies aircraft turnaround milestones from video for delay disputes", "readme_summary": "Upload stand-camera clip, delay claim and milestone log to detect loading-equipment docked to complete. Uses SAM 3.1 detection and Muse Spark 1.3 keyframe facts, then issues signed hash-verified packet.", "tech_highlights": [ "SAM 3.1 Vision", "Muse Spark 1.3", "Docker + Python" ], "created_at": "2026-10-31T12:04:02Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 19, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": true, "has_tests": true, "has_src": true, "has_ci": true, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": true, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.5, "score_meta_tooling": 1.6, "score_tech_depth": 1.7, "score_demo": 1.0, "score_total": 6.8, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Eval & benchmark proof", "+0.3" ], [ "Docker packaging", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (19)", "+0.4" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Agent / eval harness", "+0.2" ], [ "Automated CI workflow", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 144, "is_new": true, "commits_delta": 19, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "QasimAbbas-Finance/commontape-muse-agent", "html_url": "https://github.com/QasimAbbas-Finance/commontape-muse-agent", "track": "Build for Your World", "domain": "Business, Sales & Commerce", "summary": "Chat, voice or photo booking agent for local cleaning services", "readme_summary": "Parses cleaning jobs, finds local businesses, verifies exact pricing and books slots with transparent tool-call trace. Vercel app with api/lib/fixtures and tests. Powered by Muse via Meta AI for understanding and orchestration.", "tech_highlights": [ "Muse Agent", "Next.js + Vercel", "Voice + Vision Input" ], "created_at": "2026-10-26T09:19:48Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 18, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": true, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": true, "live_urls": [ "https://commontape-muse-agent.vercel.app" ], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.8, "score_meta_tooling": 2.3, "score_tech_depth": 1.3, "score_demo": 1.4, "score_total": 6.8, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ], [ "Open-weights / fine-tuning", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (18)", "+0.4" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Live web deployment", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 145, "is_new": false, "commits_delta": 0, "rank_delta": -112, "commits_delta_last_run": 0 }, { "full_name": "rrhoopes3/causeway", "html_url": "https://github.com/rrhoopes3/causeway", "track": "Push the Frontier", "domain": "Developer Tooling, Infra & Security", "summary": "Cause-tagged ledgers showing why an agent took each action.", "readme_summary": "Causeway turns tool-using agent transcripts into ledgers with IN, CARRY, GOAL, SELF tags. Muse Spark answers why-questions by citing ledger records. A verifier checks quotes exist and strikes unsupported claims.", "tech_highlights": [ "Muse Spark 1.3", "Provenance Ledger", "Citation Verifier" ], "created_at": "2026-10-26T19:50:55Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 16, "commits_before_window": 0, "prs_total": 6, "prs_merged": 1, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": true, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": true, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.0, "score_meta_tooling": 2.3, "score_tech_depth": 1.7, "score_demo": 0.8, "score_total": 6.8, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "High-impact domain", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ], [ "Open-weights / fine-tuning", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (16)", "+0.4" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Automated CI workflow", "+0.2" ], [ "PR review workflow (1 PRs)", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ] ] }, "rank": 146, "is_new": false, "commits_delta": 7, "rank_delta": 50, "commits_delta_last_run": 0 }, { "full_name": "RahulCHANDER25/jepa-as-a-tool", "html_url": "https://github.com/RahulCHANDER25/jepa-as-a-tool", "track": "Push the Frontier", "domain": "Robotics, IoT & Manufacturing", "summary": "LLM pushes a T-block after imagining moves in a V-JEPA world model.", "readme_summary": "Muse Spark plays PushT by calling a simulate tool before each real push. A frozen V-JEPA 2 encoder plus predictor imagines push sequences in latent space from images only. Translator reports predicted poses in text.", "tech_highlights": [ "V-JEPA 2 World Model", "Muse Spark", "LLM Tool-Use Agent" ], "created_at": "2026-10-26T17:23:31Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 15, "commits_before_window": 0, "prs_total": 1, "prs_merged": 1, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": true, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": true, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": true, "live_urls": [ "https://rahulchander25.github.io/jepa-as-a-tool/" ], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 1, "score_impact": 2.6, "score_meta_tooling": 1.3, "score_tech_depth": 1.7, "score_demo": 1.2, "score_total": 6.8, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "High-impact domain", "+0.4" ], [ "Eval & benchmark proof", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (15)", "+0.4" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Agent / eval harness", "+0.2" ], [ "Automated CI workflow", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Live web deployment", "+0.4" ] ] }, "rank": 147, "is_new": false, "commits_delta": 14, "rank_delta": 327, "commits_delta_last_run": 0 }, { "full_name": "sandeepvijayarao09/auren", "html_url": "https://github.com/sandeepvijayarao09/auren", "track": "Build for Your World", "domain": "Autonomous Agents & Workflow Automation", "summary": "One voice agent that carries tasks across Watch, glasses, iPhone and Mac", "readme_summary": "Muse-powered cross-device agent: say Hey Muse once and the task follows across Apple Watch, Ray-Ban Meta, iPhone and Mac. Uses Muse Wonder, Spark, Spark Open, Glimmer, Voice Transcribe and SAM 3.1. Monorepo with apps, core and docs.", "tech_highlights": [ "Muse Wonder + Spark", "Muse Voice Transcribe", "SAM 3.1" ], "created_at": "2026-10-26T20:03:32Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 3, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": true, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": true, "has_eval_benchmarks": true, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.2, "score_meta_tooling": 2.3, "score_tech_depth": 1.3, "score_demo": 1.0, "score_total": 6.8, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "High-impact domain", "+0.4" ], [ "Eval & benchmark proof", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ], [ "Open-weights / fine-tuning", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Agent / eval harness", "+0.2" ], [ "Automated CI workflow", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 148, "is_new": false, "commits_delta": 1, "rank_delta": -9, "commits_delta_last_run": 0 }, { "full_name": "pagyemang-dotcom/meaning-check", "html_url": "https://github.com/pagyemang-dotcom/meaning-check", "track": "Push the Frontier", "domain": "Developer Tooling, Infra & Security", "summary": "Tests messages against 24 AI readers to find misreadings and fix wording", "readme_summary": "Live Modal app where 16 Muse Glimmer and 8 Muse Spark readers interpret your message and show misreads. Python package with Colab, deploy, tests and docs. Finds shortest wording both model families understand.", "tech_highlights": [ "Muse Glimmer", "Muse Spark", "Modal + Python" ], "created_at": "2026-10-27T07:41:09Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 2, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": false, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": true, "has_eval_benchmarks": false, "has_setup_guide": false, "has_video_demo": true, "video_urls": [ "https://youtu.be/5yTS6-LR2_c", "https://www.youtube.com/watch?v=5yTS6-LR2_c" ], "has_live_deploy": true, "live_urls": [ "https://pagyemang-dotcom--meaning-check-web-web.us-east.modal.run/**" ], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.3, "score_meta_tooling": 1.8, "score_tech_depth": 0.6, "score_demo": 2.1, "score_total": 6.8, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "High-impact domain", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "Open-weights / fine-tuning", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "Automated test suite", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Video walkthrough", "+1.1" ], [ "Live web deployment", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 149, "is_new": true, "commits_delta": 2, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "keylorpineda/ColonQuest", "html_url": "https://github.com/keylorpineda/ColonQuest", "track": "Build for Your World", "domain": "Gaming, Entertainment & Creative Media", "summary": "2D voice-negotiation game teaching Costa Rican students money skills", "readme_summary": "Colon Quest is a 2D financial-literacy game where Muse Spark narrates monthly stories and voice sellers hide fees. A deterministic C# engine computes exact colones while AI handles story. Includes English and Spanish docs.", "tech_highlights": [ "Muse Spark 1.3", "C# Game Engine", "Voice Negotiation" ], "created_at": "2026-10-26T16:31:37Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 647, "commits_before_window": 0, "prs_total": 105, "prs_merged": 95, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": true, "has_ci": true, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": true, "has_eval_benchmarks": true, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 1, "score_impact": 2.0, "score_meta_tooling": 2.3, "score_tech_depth": 1.8, "score_demo": 0.6, "score_total": 6.7, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "General domain", "+0.2" ], [ "Eval & benchmark proof", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ], [ "Open-weights / fine-tuning", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (647)", "+0.6" ], [ "Modular src/ architecture", "+0.3" ], [ "Agent / eval harness", "+0.2" ], [ "Automated CI workflow", "+0.2" ], [ "PR review workflow (95 PRs)", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 150, "is_new": false, "commits_delta": 377, "rank_delta": -10, "commits_delta_last_run": 21 }, { "full_name": "metahackAI/a-commerce", "html_url": "https://github.com/metahackAI/a-commerce", "track": "Build for Your World", "domain": "Business, Sales & Commerce", "summary": "AI-native storefront and back-office demo with scenario-driven shopping assistance", "readme_summary": "Ailism Commerce provides storefront, back-office and fixed-clock scenarios for reproducible demos. Built in Rust with Cargo workspace, agents and crates during hackathon. Uses Meta models for conversational commerce, search and operations.", "tech_highlights": [ "Meta Models", "Rust Workspace", "AI Storefront" ], "created_at": "2026-10-27T10:08:25Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 350, "commits_before_window": 0, "prs_total": 107, "prs_merged": 81, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": true, "has_ci": true, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": true, "has_eval_benchmarks": true, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.1, "score_meta_tooling": 1.8, "score_tech_depth": 1.8, "score_demo": 1.0, "score_total": 6.7, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Eval & benchmark proof", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "Open-weights / fine-tuning", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (350)", "+0.6" ], [ "Modular src/ architecture", "+0.3" ], [ "Agent / eval harness", "+0.2" ], [ "Automated CI workflow", "+0.2" ], [ "PR review workflow (81 PRs)", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 151, "is_new": false, "commits_delta": 335, "rank_delta": 75, "commits_delta_last_run": 0 }, { "full_name": "Nandish3010/categoryos", "html_url": "https://github.com/Nandish3010/categoryos", "track": "Build for Your World", "domain": "Business, Sales & Commerce", "summary": "Agentic category manager that vets vendors and proves every number", "readme_summary": "Screens new vendors for documents and injection, decides SKU bets and terms, then monitors category. Deterministic verifiers prove numbers on synthetic data. Backend plus frontend stack recorded live against Muse Spark, Muse Image and SAM 3.1.", "tech_highlights": [ "Muse Spark", "SAM 3.1 Vision", "Agentic Verifiers" ], "created_at": "2026-10-26T18:59:42Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 171, "commits_before_window": 0, "prs_total": 41, "prs_merged": 41, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": true, "has_ci": true, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": true, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.1, "score_meta_tooling": 1.8, "score_tech_depth": 1.8, "score_demo": 1.0, "score_total": 6.7, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Eval & benchmark proof", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (171)", "+0.6" ], [ "Modular src/ architecture", "+0.3" ], [ "Agent / eval harness", "+0.2" ], [ "Automated CI workflow", "+0.2" ], [ "PR review workflow (41 PRs)", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 152, "is_new": true, "commits_delta": 171, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "Cirorx/ronda", "html_url": "https://github.com/Cirorx/ronda", "track": "Build for Your World", "domain": "Healthcare, Civic Tech & Sustainability", "summary": "Weekly small groups match five nearby neighbours for recurring meetups.", "readme_summary": "Ronda forms stable groups of five neighbours for weekly meetups like mate or futbol. Built as a mobile app with Firebase and docs-driven design. Uses Meta AI models for matching and coordination during the hackathon build window.", "tech_highlights": [ "Flutter + Firebase", "Muse Spark", "Group Matching" ], "created_at": "2026-10-26T21:17:29Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 106, "commits_before_window": 0, "prs_total": 6, "prs_merged": 1, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": true, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": true, "has_eval_benchmarks": false, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.9, "score_meta_tooling": 2.3, "score_tech_depth": 1.9, "score_demo": 0.6, "score_total": 6.7, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "High-impact domain", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ], [ "Open-weights / fine-tuning", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (106)", "+0.6" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Automated CI workflow", "+0.2" ], [ "PR review workflow (1 PRs)", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 153, "is_new": false, "commits_delta": 64, "rank_delta": -66, "commits_delta_last_run": 5 }, { "full_name": "AariaSec/witness", "html_url": "https://github.com/AariaSec/witness", "track": "Push the Frontier", "domain": "Developer Tooling, Infra & Security", "summary": "Independent content-free recorder that audits AI coding-agent actions", "readme_summary": "Compares agent self-reports against out-of-process records of file writes, network and processes. Stores only digests, counts and timestamps, no prompt text. Includes live console, schemas, corpus and Muse plugin.", "tech_highlights": [ "Agent Audit Trail", "Content-Free Digests", "Python + Web Console" ], "created_at": "2026-10-26T16:37:36Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 83, "commits_before_window": 0, "prs_total": 4, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": true, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": true, "live_urls": [ "https://aariasec.github.io/witness/" ], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.3, "score_meta_tooling": 1.3, "score_tech_depth": 1.7, "score_demo": 1.4, "score_total": 6.7, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "High-impact domain", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (83)", "+0.6" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Automated CI workflow", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Live web deployment", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 154, "is_new": false, "commits_delta": 1, "rank_delta": -94, "commits_delta_last_run": 0 }, { "full_name": "nankris/tokentrim-meta", "html_url": "https://github.com/nankris/tokentrim-meta", "track": "Push the Frontier", "domain": "Developer Tooling, Infra & Security", "summary": "Skill-first optimizer cuts billed cost per successful agent task", "readme_summary": "TokenTrim adds caching, compaction and tool modules for coding agents on Meta Model API. Python CLI + dashboard measures dollars per successful task using muse-spark-1.3-contributor on synthetic benchmarks.", "tech_highlights": [ "Muse Spark 1.3", "Token Optimization", "Python Benchmarks" ], "created_at": "2026-10-29T17:15:17Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 41, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": true, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.6, "score_meta_tooling": 1.6, "score_tech_depth": 1.5, "score_demo": 1.0, "score_total": 6.7, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "High-impact domain", "+0.4" ], [ "Eval & benchmark proof", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (41)", "+0.4" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Agent / eval harness", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 155, "is_new": true, "commits_delta": 41, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "Thomas-Jerard/cozzo-canary-caller", "html_url": "https://github.com/Thomas-Jerard/cozzo-canary-caller", "track": "Push the Frontier", "domain": "Developer Tooling, Infra & Security", "summary": "Adversarial caller that stress-tests voice agents with difficult scenarios", "readme_summary": "AI mystery shopper sends difficult callers at voice agents before launch and grades pass-fail in re-runnable grid. Muse Wonder generates adversarial scenarios from business URL. Text transcripts plus browser-voice playback for review.", "tech_highlights": [ "Muse Wonder", "Voice Agent Eval", "Next.js + Browser TTS" ], "created_at": "2026-10-26T21:19:32Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 27, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": true, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.6, "score_meta_tooling": 1.6, "score_tech_depth": 1.5, "score_demo": 1.0, "score_total": 6.7, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "High-impact domain", "+0.4" ], [ "Eval & benchmark proof", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (27)", "+0.4" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Agent / eval harness", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 156, "is_new": false, "commits_delta": 8, "rank_delta": -82, "commits_delta_last_run": 0 }, { "full_name": "rankallstartup-cell/rankall-video-report", "html_url": "https://github.com/rankallstartup-cell/rankall-video-report", "track": "Build for Your World", "domain": "Business, Sales & Commerce", "summary": "Turns an AI-visibility scan into a personalized video report for businesses", "readme_summary": "Scans a business for AI search visibility then generates a presenter-led video report from real scan numbers with one-click written report. Built with Next.js, app/components/lib structure and e2e tests. Uses Meta AI models for report narration and video generation pipeline.", "tech_highlights": [ "Next.js + Vercel", "AI Video Reports", "Muse Spark 1.3" ], "created_at": "2026-10-26T22:43:15Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 19, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": true, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": false, "has_video_demo": true, "video_urls": [ "https://rankall-git-hackathon-video-report-nandish-patel-s-projects.vercel.app/demo-walkthrough-v3.mp4" ], "has_live_deploy": true, "live_urls": [ "https://rankall-git-hackathon-video-report-nandish-patel-s-projects.vercel.app/hackathon/video-report/judge", "https://rankall-git-hackathon-video-report-nandish-patel-s-projects.vercel.app/hackathon/video-report", "https://rankall-git-hackathon-video-report-nandish-patel-s-projects.vercel.app/demo-walkthrough-v3.mp4", "https://rankall-git-hackathon-video-report-nandish-patel-s-projects.vercel.app/demo-walkthrough-v3.mp4." ], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.8, "score_meta_tooling": 1.3, "score_tech_depth": 1.5, "score_demo": 2.1, "score_total": 6.7, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (19)", "+0.4" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Automated CI workflow", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Video walkthrough", "+1.1" ], [ "Live web deployment", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 157, "is_new": false, "commits_delta": 19, "rank_delta": 351, "commits_delta_last_run": 0 }, { "full_name": "LincForge/nerve-muse-sam", "html_url": "https://github.com/LincForge/nerve-muse-sam", "track": "Push the Frontier", "domain": "Developer Tooling, Infra & Security", "summary": "Gives Muse hands and eyes on phones and watches via MCP with bench tests", "readme_summary": "Provides physical-device control of Android, Wear OS and iOS simulators via MCP linc-nerve server. Evaluated under pre-registered confinement on mobile-agent-bench. Uses Muse Spark 1.3 for agency and SAM 3.1 for screen vision.", "tech_highlights": [ "Muse Spark 1.3", "SAM 3.1 Vision", "MCP + AgentBench" ], "created_at": "2026-10-27T17:50:08Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 11, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": true, "has_eval_benchmarks": false, "has_setup_guide": false, "has_video_demo": true, "video_urls": [ "https://youtu.be/9S16V0PKQuY" ], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.1, "score_meta_tooling": 1.8, "score_tech_depth": 1.1, "score_demo": 1.7, "score_total": 6.7, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "High-impact domain", "+0.4" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ], [ "Open-weights / fine-tuning", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "5+ window commits (11)", "+0.2" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Video walkthrough", "+1.1" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 158, "is_new": false, "commits_delta": 4, "rank_delta": 39, "commits_delta_last_run": 0 }, { "full_name": "MoriaCrew/Pinned", "html_url": "https://github.com/MoriaCrew/Pinned", "track": "Build for Your World", "domain": "Gaming, Entertainment & Creative Media", "summary": "Shared photo board where friends cut out objects and remix them into new scenes", "readme_summary": "Pinneds lets friends drop photos on one board, segments objects with Meta vision models and remixes pins into credited scenes. Solo Indie Build for Your World app at pinneds.com, using Muse Image generation and Muse Spark narration.", "tech_highlights": [ "SAM Segmentation", "Muse Image", "Firebase Hosting" ], "created_at": "2026-10-26T14:43:22Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 10, "commits_before_window": 0, "prs_total": 214, "prs_merged": 205, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": true, "meta_api_verified": true, "partner_infra": "Together", "open_weights_tuning": false, "has_eval_benchmarks": true, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.0, "score_meta_tooling": 2.0, "score_tech_depth": 1.7, "score_demo": 1.0, "score_total": 6.7, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "General domain", "+0.2" ], [ "Eval & benchmark proof", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ], [ "Partner inference infra", "+0.2" ] ], "tech": [ [ "Base", "+0.3" ], [ "5+ window commits (10)", "+0.2" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Agent / eval harness", "+0.2" ], [ "Automated CI workflow", "+0.2" ], [ "PR review workflow (205 PRs)", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 159, "is_new": false, "commits_delta": 1, "rank_delta": -49, "commits_delta_last_run": 0 }, { "full_name": "VivekChaurasiya95/Meridian-AI", "html_url": "https://github.com/VivekChaurasiya95/Meridian-AI", "track": "Push the Frontier", "domain": "Developer Tooling, Infra & Security", "summary": "Turns messy bug reports into reproducible evidence with capture and verification", "readme_summary": "Meridian AI converts bug reports into reproduced, captured, and verified evidence for engineering teams. Stack is Node 20 web app plus Python 3.12 FastAPI service with Postgres, Alembic, and Docker Compose. Uses Meta AI / Muse models to parse reports and assist reproduction workflow.", "tech_highlights": [ "FastAPI + Next.js", "Postgres + Docker", "Muse Model Assist" ], "created_at": "2026-10-27T23:13:31Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 8, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": true, "has_tests": false, "has_src": true, "has_ci": true, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": true, "video_urls": [ "https://www.youtube.com/watch?v=YOUR_VIDEO_ID" ], "has_live_deploy": true, "live_urls": [ "https://vivek-chaurasiya.vercel.app" ], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.7, "score_meta_tooling": 0.5, "score_tech_depth": 1.0, "score_demo": 2.5, "score_total": 6.7, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "High-impact domain", "+0.4" ], [ "Docker packaging", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "5+ window commits (8)", "+0.2" ], [ "Modular src/ architecture", "+0.3" ], [ "Automated CI workflow", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Video walkthrough", "+1.1" ], [ "Reproducible setup guide", "+0.4" ], [ "Live web deployment", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 160, "is_new": false, "commits_delta": 6, "rank_delta": 309, "commits_delta_last_run": 0 }, { "full_name": "mrfentmen/meta-sentinel", "html_url": "https://github.com/mrfentmen/meta-sentinel", "track": "Push the Frontier", "domain": "Developer Tooling, Infra & Security", "summary": "Agent OS platform where watch, lab and workshop systems plug in as places", "readme_summary": "Repo mirrors Meta OS platform: systems plug in like city departments for agents. Rust + Node codebase with extensive tests. Built for hackathon as always-on agent infrastructure.", "tech_highlights": [ "Rust + Node.js", "Agent Platform", "Muse Relay" ], "created_at": "2026-10-28T10:47:33Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 676, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": true, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": true, "live_urls": [ "https://muse-relay-live.pages.dev", "https://meta-os.pages.dev" ], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.6, "score_meta_tooling": 1.3, "score_tech_depth": 1.7, "score_demo": 1.0, "score_total": 6.6, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "High-impact domain", "+0.4" ], [ "Eval & benchmark proof", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (676)", "+0.6" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Agent / eval harness", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Live web deployment", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 161, "is_new": false, "commits_delta": 507, "rank_delta": 16, "commits_delta_last_run": 22 }, { "full_name": "mrfentmen/meta-os", "html_url": "https://github.com/mrfentmen/meta-os", "track": "Push the Frontier", "domain": "Developer Tooling, Infra & Security", "summary": "Agent OS platform where watch, lab and workshop systems plug in as places", "readme_summary": "Meta OS is a Rust + Node platform for AI agents to work in persistent systems. Modular worlds packs with large test suites and live crew viewer. Built for hackathon as always-on agent infrastructure.", "tech_highlights": [ "Rust + Node.js", "Agent Platform", "Muse Relay" ], "created_at": "2026-10-28T10:47:33Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 676, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": true, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": true, "live_urls": [ "https://muse-relay-live.pages.dev", "https://meta-os.pages.dev" ], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.6, "score_meta_tooling": 1.3, "score_tech_depth": 1.7, "score_demo": 1.0, "score_total": 6.6, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "High-impact domain", "+0.4" ], [ "Eval & benchmark proof", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (676)", "+0.6" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Agent / eval harness", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Live web deployment", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 162, "is_new": true, "commits_delta": 676, "rank_delta": 0, "commits_delta_last_run": 22 }, { "full_name": "meta-ai-hackathon/meta-hack", "html_url": "https://github.com/meta-ai-hackathon/meta-hack", "track": "Build for Your World", "domain": "Healthcare, Civic Tech & Sustainability", "summary": "Guided North Carolina Medicaid application navigator with form mapping", "readme_summary": "Benefits Navigator guides initial MAGI Medicaid journey including self-employment income case. Dockerized app with architecture contract and 128 validation assertions. Uses Meta AI models to guide paperwork and map DHB-5200 forms.", "tech_highlights": [ "Meta AI Navigator", "Docker + CI", "Form Mapping Engine" ], "created_at": "2026-10-26T21:51:45Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 571, "commits_before_window": 0, "prs_total": 106, "prs_merged": 99, "is_preexisting": false, "has_docker": true, "has_tests": true, "has_src": true, "has_ci": true, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": true, "live_urls": [ "https://meta-hack-omega.vercel.app" ], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.3, "score_meta_tooling": 1.0, "score_tech_depth": 1.9, "score_demo": 1.4, "score_total": 6.6, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "High-impact domain", "+0.4" ], [ "Docker packaging", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (571)", "+0.6" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Automated CI workflow", "+0.2" ], [ "PR review workflow (99 PRs)", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Live web deployment", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 163, "is_new": false, "commits_delta": 470, "rank_delta": 15, "commits_delta_last_run": 9 }, { "full_name": "rehaancubess/muselaunch", "html_url": "https://github.com/rehaancubess/muselaunch", "track": "Build for Your World", "domain": "Business, Sales & Commerce", "summary": "AI growth studio that researches markets and cuts promo videos from real app footage", "readme_summary": "Connects an indie app, researches market, plans campaigns and produces editable 30-60s promo videos. Monorepo with web apps and packages; uses Muse models, SAM 3.1 and HyperFrames for video generation.", "tech_highlights": [ "Muse Models", "SAM 3.1 Vision", "HyperFrames Video" ], "created_at": "2026-10-28T08:01:52Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 248, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": true, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.8, "score_meta_tooling": 2.3, "score_tech_depth": 1.5, "score_demo": 1.0, "score_total": 6.6, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ], [ "Open-weights / fine-tuning", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (248)", "+0.6" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 164, "is_new": false, "commits_delta": 47, "rank_delta": -88, "commits_delta_last_run": 0 }, { "full_name": "Parithosh-Varma/snapclaim", "html_url": "https://github.com/Parithosh-Varma/snapclaim", "track": "Build for Your World", "domain": "Finance, Crypto & Web3", "summary": "Turns a damage photo plus voice line into a measured claim-ready evidence pack", "readme_summary": "Builds replayable evidence from damage photo and speech with calibrated measurements for damage percent, crack size and area using any known-size reference. AI findings ship only with machine-checkable receipts. Language and currency agnostic with auto voice detection.", "tech_highlights": [ "Vision Measurement", "Voice Auto-Detect", "Receipt Verification" ], "created_at": "2026-10-27T14:57:59Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 228, "commits_before_window": 0, "prs_total": 47, "prs_merged": 24, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": true, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": true, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": true, "live_urls": [ "https://snapclaim.pages.dev", "https://snapclaim.pages.dev/admin", "https://snapclaim.pages.dev/", "https://snapclaim-backend.parithosh.workers.dev" ], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 2, "score_impact": 2.1, "score_meta_tooling": 1.1, "score_tech_depth": 2.0, "score_demo": 1.4, "score_total": 6.6, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Eval & benchmark proof", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (228)", "+0.6" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Agent / eval harness", "+0.2" ], [ "Automated CI workflow", "+0.2" ], [ "PR review workflow (24 PRs)", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Live web deployment", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 165, "is_new": true, "commits_delta": 228, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "Izaansherif/page-ledger", "html_url": "https://github.com/Izaansherif/page-ledger", "track": "Build for Your World", "domain": "Business, Sales & Commerce", "summary": "Photo of a paper shop notebook becomes a searchable mini-CRM with one-tap WhatsApp", "readme_summary": "Converts ledger photos into customers, balances and follow-up lists. Stack is vanilla HTML/CSS/JS ES modules with Supabase and Netlify Functions, zero npm dependencies. Uses Muse Spark Open for reading and Q&A and Muse Voice Transcribe via netlify/functions/_lib/ai.js.", "tech_highlights": [ "Muse Spark Open", "Muse Voice Transcribe", "Supabase + Netlify" ], "created_at": "2026-10-26T14:51:36Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 67, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": true, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.8, "score_meta_tooling": 2.3, "score_tech_depth": 1.5, "score_demo": 1.0, "score_total": 6.6, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ], [ "Open-weights / fine-tuning", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (67)", "+0.6" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 166, "is_new": false, "commits_delta": 20, "rank_delta": -22, "commits_delta_last_run": 0 }, { "full_name": "oherna25/trading_bot_project", "html_url": "https://github.com/oherna25/trading_bot_project", "track": "Build for Your World", "domain": "Finance, Crypto & Web3", "summary": "Research-first options system with GEX analytics, replay and paper trading", "readme_summary": "Options research and paper-trading system computing GEX/VEX/DEX from stored snapshots. Provides regime read, trade cards, backtests, shock tests and chat research. Journals signals with Discord/Telegram alerts; live trading gated.", "tech_highlights": [ "Python Trading Bot", "GEX Analytics", "Paper Trading" ], "created_at": "2026-10-27T17:08:37Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 34, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": true, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": true, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 1, "score_impact": 2.1, "score_meta_tooling": 1.8, "score_tech_depth": 1.7, "score_demo": 1.0, "score_total": 6.6, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Eval & benchmark proof", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (34)", "+0.4" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Agent / eval harness", "+0.2" ], [ "Automated CI workflow", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 167, "is_new": true, "commits_delta": 34, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "rishulmatta/shifu", "html_url": "https://github.com/rishulmatta/shifu", "track": "Build for Your World", "domain": "Education & Knowledge Systems", "summary": "Turns best YouTube moments into lessons with checks until it sticks", "readme_summary": "Next.js app that curates YouTube clips per topic and quizzes for retention. Deployed with Baseten and Modal hosting. Uses Muse Spark 1.3 for tutoring and Muse Voice Transcribe for video speech.", "tech_highlights": [ "Muse Spark 1.3", "Muse Voice Transcribe", "Next.js + Baseten" ], "created_at": "2026-10-26T22:30:19Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 32, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": false, "meta_api_verified": true, "partner_infra": "Baseten", "open_weights_tuning": true, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.8, "score_meta_tooling": 2.5, "score_tech_depth": 1.3, "score_demo": 1.0, "score_total": 6.6, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ], [ "Partner inference infra", "+0.2" ], [ "Open-weights / fine-tuning", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (32)", "+0.4" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 168, "is_new": false, "commits_delta": 2, "rank_delta": -96, "commits_delta_last_run": 0 }, { "full_name": "Michael2540/CERES", "html_url": "https://github.com/Michael2540/CERES", "track": "Push the Frontier", "domain": "Robotics, IoT & Manufacturing", "summary": "Autonomous crop-health monitor for Mars greenhouses that detects wilt and alerts offline", "readme_summary": "CERES is mission control for off-Earth farming that measures plants, raises evidence-backed alerts, and works without Earth link. Built for the Meta hackathon, it uses Meta models for detection and explanation with human-verified decisions and offline-first architecture.", "tech_highlights": [ "Muse Spark", "Offline-First Edge", "Plant Vision Detection" ], "created_at": "2026-10-26T19:00:16Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 18, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": true, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.3, "score_meta_tooling": 1.8, "score_tech_depth": 1.5, "score_demo": 1.0, "score_total": 6.6, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "High-impact domain", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (18)", "+0.4" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Automated CI workflow", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 169, "is_new": false, "commits_delta": 15, "rank_delta": 183, "commits_delta_last_run": 0 }, { "full_name": "bigse0u1/ReActSim", "html_url": "https://github.com/bigse0u1/ReActSim", "track": "Push the Frontier", "domain": "Robotics, IoT & Manufacturing", "summary": "Closed-loop robot agent that imagines, acts, and replans after failures", "readme_summary": "Franka Panda in ManiSkill 3 uses SAM 3.1 for detection and Muse Spark for skill planning on YCB objects. Detects disturbances like knocked objects from physics state and replans. Evaluated with 120 runs and Fisher exact tests.", "tech_highlights": [ "SAM 3.1 Vision", "Muse Spark 1.3", "ManiSkill 3" ], "created_at": "2026-10-26T09:41:51Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 18, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": true, "live_urls": [ "https://cerebralvalley.ai/e/meta-ai-developer-hackathon" ], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.3, "score_meta_tooling": 1.6, "score_tech_depth": 1.3, "score_demo": 1.4, "score_total": 6.6, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "High-impact domain", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (18)", "+0.4" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Live web deployment", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 170, "is_new": false, "commits_delta": 5, "rank_delta": -76, "commits_delta_last_run": 0 }, { "full_name": "SrishtiDesai/hull-ultimax", "html_url": "https://github.com/SrishtiDesai/hull-ultimax", "track": "Push the Frontier", "domain": "Robotics, IoT & Manufacturing", "summary": "AI engineer designs sub hulls and refuses unsafe ones via physics test", "readme_summary": "Muse Spark 1.3 design agent proposes submarine hulls, calls Python fatigue physics tool, and explains refusals. Includes MCP server, benchmarks vs one-shot baseline, red-team prompts and demo site.", "tech_highlights": [ "Muse Spark 1.3", "Physics Tool Use", "MCP Server + Python" ], "created_at": "2026-10-29T19:16:56Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 17, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": false, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": true, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": true, "live_urls": [ "https://srishtidesai.github.io/hull-ultimax/" ], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 1, "score_impact": 2.6, "score_meta_tooling": 1.8, "score_tech_depth": 1.2, "score_demo": 1.0, "score_total": 6.6, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "High-impact domain", "+0.4" ], [ "Eval & benchmark proof", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (17)", "+0.4" ], [ "Automated test suite", "+0.3" ], [ "Agent / eval harness", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Live web deployment", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 171, "is_new": true, "commits_delta": 17, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "Josephjbassey/omnistore-ai", "html_url": "https://github.com/Josephjbassey/omnistore-ai", "track": "Build for Your World", "domain": "Business, Sales & Commerce", "summary": "Camera-first storefront builder for micro-vendors with auto pricing", "readme_summary": "Decoupled Next.js 14 App Router frontend and FastAPI engine for micro-commerce. Pipeline is SAM 3.1 for product vision, Muse Spark 1.3 for reasoning, Muse Code for actions. Targets kiosk vendors.", "tech_highlights": [ "SAM 3.1 Vision", "Muse Spark 1.3", "Next.js + FastAPI" ], "created_at": "2026-10-27T09:55:11Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 16, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": true, "has_tests": false, "has_src": true, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": true, "live_urls": [ "https://omnistore-demo.vercel.app/mama-cass-market", "https://omnistore-sandy.vercel.app" ], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.2, "score_meta_tooling": 1.8, "score_tech_depth": 1.2, "score_demo": 1.4, "score_total": 6.6, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Docker packaging", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (16)", "+0.4" ], [ "Modular src/ architecture", "+0.3" ], [ "Agent / eval harness", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Live web deployment", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 172, "is_new": true, "commits_delta": 16, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "asjames18/sightwork-hackathon", "html_url": "https://github.com/asjames18/sightwork-hackathon", "track": "Build for Your World", "domain": "Multimodal Vision & Video (SAM / Vision)", "summary": "Turns phone walkthrough video into ranked property work plan with proof", "readme_summary": "Films one walkthrough to return inventory counts, ranked Fix now/soon/wait problems, and proof frames. Next.js TypeScript app with Playwright e2e and CI. Uses Meta AI vision models to detect issues and extract materials from video frames.", "tech_highlights": [ "Vision Video Analysis", "Next.js + TypeScript", "Playwright E2E" ], "created_at": "2026-10-26T10:46:25Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 780, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": true, "has_ci": true, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": true, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.8, "score_meta_tooling": 2.3, "score_tech_depth": 1.4, "score_demo": 1.0, "score_total": 6.5, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ], [ "Open-weights / fine-tuning", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (780)", "+0.6" ], [ "Modular src/ architecture", "+0.3" ], [ "Automated CI workflow", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 173, "is_new": false, "commits_delta": 563, "rank_delta": -8, "commits_delta_last_run": 14 }, { "full_name": "Bridgett50/second-seat-hackathon", "html_url": "https://github.com/Bridgett50/second-seat-hackathon", "track": "Build for Your World", "domain": "Autonomous Agents & Workflow Automation", "summary": "AI meeting twin that attends, masks sensitive details, and drafts follow-ups", "readme_summary": "Second Seat is a scripted meeting room where an AI twin participates with live guidance and takeover. It masks sensitive data, keeps evidence records and drafts follow-ups for review. Solo-founder privacy safety layer.", "tech_highlights": [ "AI Meeting Twin", "Privacy Masking", "Evidence Record" ], "created_at": "2026-10-26T16:56:58Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 519, "commits_before_window": 0, "prs_total": 156, "prs_merged": 101, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": true, "has_ci": true, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": true, "has_eval_benchmarks": true, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.2, "score_meta_tooling": 1.5, "score_tech_depth": 1.8, "score_demo": 1.0, "score_total": 6.5, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "High-impact domain", "+0.4" ], [ "Eval & benchmark proof", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ], [ "Open-weights / fine-tuning", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (519)", "+0.6" ], [ "Modular src/ architecture", "+0.3" ], [ "Agent / eval harness", "+0.2" ], [ "Automated CI workflow", "+0.2" ], [ "PR review workflow (101 PRs)", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 174, "is_new": false, "commits_delta": 161, "rank_delta": -18, "commits_delta_last_run": 0 }, { "full_name": "KevinKbyte/MemriPal", "html_url": "https://github.com/KevinKbyte/MemriPal", "track": "Build for Your World", "domain": "Education & Knowledge Systems", "summary": "Turns familiar places into memory palaces for speeches and exam recall", "readme_summary": "Photographs a familiar space, SAM 3.1 segments loci into a walking route, Muse Spark creates associations, Muse Image renders scenes. Deterministic matcher scores Muse Voice transcripts. Runs live via Meta Model API or offline fixtures.", "tech_highlights": [ "SAM 3.1 Vision", "Muse Spark 1.3", "Muse Voice + Image" ], "created_at": "2026-10-26T16:53:15Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 512, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": true, "has_tests": true, "has_src": true, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.2, "score_meta_tooling": 1.8, "score_tech_depth": 1.5, "score_demo": 1.0, "score_total": 6.5, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Docker packaging", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (512)", "+0.6" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 175, "is_new": false, "commits_delta": 211, "rank_delta": -151, "commits_delta_last_run": 0 }, { "full_name": "PearlLeeStudio/TheArtist-DAW", "html_url": "https://github.com/PearlLeeStudio/TheArtist-DAW", "track": "Build for Your World", "domain": "Gaming, Entertainment & Creative Media", "summary": "AI arrangement assistant that turns sketches into harmony and DAW-ready tracks", "readme_summary": "Takes scores or chord sketches to shape harmony, form and accompaniment, then continues in a DAW. Web app with backend and agent workflow for arrangement suggestions. Uses Meta Muse Spark 1.3 for music reasoning.", "tech_highlights": [ "Muse Spark 1.3", "AI Arrangement", "DAW Integration" ], "created_at": "2026-10-27T13:36:38Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 265, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": false, "has_video_demo": true, "video_urls": [ "https://youtu.be/iSDj4VK9nKc" ], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.7, "score_meta_tooling": 1.6, "score_tech_depth": 1.5, "score_demo": 1.7, "score_total": 6.5, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "General domain", "+0.2" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "Published HF Hub weights", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (265)", "+0.6" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Video walkthrough", "+1.1" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 176, "is_new": false, "commits_delta": 162, "rank_delta": -150, "commits_delta_last_run": 0 }, { "full_name": "nathandavidgreene/ancientos-hackathon", "html_url": "https://github.com/nathandavidgreene/ancientos-hackathon", "track": "Push the Frontier", "domain": "Developer Tooling, Infra & Security", "summary": "Agent OS that separates intelligence, approval, execution, and audit log", "readme_summary": "Proposes with local Llama privacy router and cloud models, gates actions by approval bound to payload hash, executes once, logs hash-chained evidence. Rust crates plus CLI and docs. Uses Meta cloud models + Llama local.", "tech_highlights": [ "Llama Local + Cloud", "Auth Gate + Audit Log", "Rust Agent OS" ], "created_at": "2026-10-26T16:46:52Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 161, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": true, "has_ci": true, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.3, "score_meta_tooling": 1.8, "score_tech_depth": 1.4, "score_demo": 1.0, "score_total": 6.5, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "High-impact domain", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (161)", "+0.6" ], [ "Modular src/ architecture", "+0.3" ], [ "Automated CI workflow", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 177, "is_new": false, "commits_delta": 67, "rank_delta": 46, "commits_delta_last_run": 0 }, { "full_name": "BoMa-AI-Cloud/aria-home", "html_url": "https://github.com/BoMa-AI-Cloud/aria-home", "track": "Build for Your World", "domain": "Healthcare, Civic Tech & Sustainability", "summary": "Checks if an elder's home will be warm by morning and who should respond", "readme_summary": "10-step warm-by story shows verdict, current house state, and responder guidance from synthetic sensor data. Frontend + backend demo on Render, no sign-in. Indie entry focused on early fault detection, not control or medical advice.", "tech_highlights": [ "Render Demo", "Synthetic IoT", "Meta AI Entry" ], "created_at": "2026-10-26T16:23:35Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 112, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": true, "has_ci": true, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": true, "live_urls": [ "https://aria-home-demo.onrender.com" ], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.9, "score_meta_tooling": 1.8, "score_tech_depth": 1.4, "score_demo": 1.4, "score_total": 6.5, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "High-impact domain", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (112)", "+0.6" ], [ "Modular src/ architecture", "+0.3" ], [ "Automated CI workflow", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Live web deployment", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 178, "is_new": false, "commits_delta": 22, "rank_delta": -88, "commits_delta_last_run": 2 }, { "full_name": "Josezx18/muselearn", "html_url": "https://github.com/Josezx18/muselearn", "track": "Build for Your World", "domain": "Education & Knowledge Systems", "summary": "Study planner that tutors without doing homework and verifies learning", "readme_summary": "Platform for teachers and secondary students with classes, tasks and submissions in Spanish/English. Live Vercel demo with Supabase auth and seed data. Uses Muse models for weekly planning, tutoring and understanding checks.", "tech_highlights": [ "Muse Spark", "Next.js + Supabase", "Vercel Demo" ], "created_at": "2026-10-27T18:50:06Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 105, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": true, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": true, "live_urls": [ "https://muselearn-five.vercel.app", "https://muselearn-five.vercel.app/en/como-funciona", "https://muselearn-five.vercel.app/es/como-funciona" ], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.8, "score_meta_tooling": 1.8, "score_tech_depth": 1.5, "score_demo": 1.4, "score_total": 6.5, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "Open-weights / fine-tuning", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (105)", "+0.6" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Live web deployment", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 179, "is_new": false, "commits_delta": 62, "rank_delta": -128, "commits_delta_last_run": 0 }, { "full_name": "TengKianBoon/fieldproof", "html_url": "https://github.com/TengKianBoon/fieldproof", "track": "Build for Your World", "domain": "Healthcare, Civic Tech & Sustainability", "summary": "Client or agent hires field workers to collect verifiable photo evidence", "readme_summary": "FieldProof lets clients or AI agents post field jobs that workers complete guided on mobile. Muse Spark reads labels and drafts evidence reports for human decision. Web app deployed on Netlify with MIT license.", "tech_highlights": [ "Muse Spark", "Netlify Web App", "AI Agent Drafting" ], "created_at": "2026-10-30T02:34:21Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 80, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": true, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": true, "video_urls": [ "https://github.com/TengKianBoon/fieldproof/releases/download/fieldproof-demo-2026-10-30/fieldproof-demo.mp4" ], "has_live_deploy": true, "live_urls": [ "https://fieldproof-180climate.netlify.app" ], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.7, "score_meta_tooling": 1.1, "score_tech_depth": 1.2, "score_demo": 2.5, "score_total": 6.5, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "High-impact domain", "+0.4" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (80)", "+0.6" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Video walkthrough", "+1.1" ], [ "Reproducible setup guide", "+0.4" ], [ "Live web deployment", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 180, "is_new": true, "commits_delta": 80, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "henryweimd/cozy-peptide", "html_url": "https://github.com/henryweimd/cozy-peptide", "track": "Build for Your World", "domain": "Healthcare, Civic Tech & Sustainability", "summary": "Designs novel safety-checked peptides from a disease name in the browser", "readme_summary": "Browser app where Muse Spark 1.3 invents peptides, then compiler verifies safety and compiles to DNA for live biotherapeutics. Next.js + ML pipeline deployed on Vercel. Includes biology, safety, and API explainers.", "tech_highlights": [ "Muse Spark 1.3", "Next.js + Vercel", "Peptide Compiler" ], "created_at": "2026-10-31T00:37:52Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 75, "commits_before_window": 0, "prs_total": 10, "prs_merged": 10, "is_preexisting": false, "has_docker": true, "has_tests": true, "has_src": true, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": true, "live_urls": [ "https://cozy-peptide.vercel.app/", "https://cozy-peptide.vercel.app/biology", "https://cozy-peptide.vercel.app/#responsible-use-meta-ai-tooling", "https://cozy-peptide.vercel.app/#demo", "https://cozy-peptide.vercel.app/#pipeline", "https://cozy-peptide.vercel.app/#api", "https://cozy-peptide.vercel.app" ], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.3, "score_meta_tooling": 1.1, "score_tech_depth": 1.7, "score_demo": 1.4, "score_total": 6.5, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "High-impact domain", "+0.4" ], [ "Docker packaging", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (75)", "+0.6" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "PR review workflow (10 PRs)", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Live web deployment", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 181, "is_new": true, "commits_delta": 75, "rank_delta": 0, "commits_delta_last_run": 6 }, { "full_name": "AUsernameForYou/agenthand", "html_url": "https://github.com/AUsernameForYou/agenthand", "track": "Build for Your World", "domain": "Business, Sales & Commerce", "summary": "MCP server that turns messy product photos into listing-ready images", "readme_summary": "MCP server for selling agents with draw, cut_out, and identify tools. Python MCP stack segments products and composites them into scenes. Uses Meta AI vision models for planning, segmentation, and fidelity-checked generation.", "tech_highlights": [ "MCP Server", "Vision Segmentation", "Muse Models" ], "created_at": "2026-10-27T00:30:43Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 63, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": true, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": true, "live_urls": [ "https://ausernameforyou.github.io/agenthand/#fidelity" ], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.8, "score_meta_tooling": 1.6, "score_tech_depth": 1.7, "score_demo": 1.4, "score_total": 6.5, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (63)", "+0.6" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Automated CI workflow", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Live web deployment", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 182, "is_new": false, "commits_delta": 0, "rank_delta": -120, "commits_delta_last_run": 0 }, { "full_name": "QiaoyuYang/questory", "html_url": "https://github.com/QiaoyuYang/questory", "track": "Build for Your World", "domain": "Gaming, Entertainment & Creative Media", "summary": "A walking mystery game that turns street photos into cases solved on foot.", "readme_summary": "Questory is a mobile-first Next.js 16 game where agent Wren builds a case from player photos. It uses Meta Model API with Muse for story reasoning and SAM 3.1 for vision evidence, served from questory.run.", "tech_highlights": [ "SAM 3.1 Vision", "Muse Models", "Next.js 16" ], "created_at": "2026-10-26T16:34:25Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 61, "commits_before_window": 0, "prs_total": 60, "prs_merged": 59, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": true, "has_ci": true, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": true, "live_urls": [ "https://questory.run" ], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.7, "score_meta_tooling": 1.8, "score_tech_depth": 1.6, "score_demo": 1.4, "score_total": 6.5, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "General domain", "+0.2" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (61)", "+0.6" ], [ "Modular src/ architecture", "+0.3" ], [ "Automated CI workflow", "+0.2" ], [ "PR review workflow (59 PRs)", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Live web deployment", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 183, "is_new": true, "commits_delta": 61, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "ahk1542001-wq/pageops-agent", "html_url": "https://github.com/ahk1542001-wq/pageops-agent", "track": "Build for Your World", "domain": "Business, Sales & Commerce", "summary": "Approval-gated agent running weekly social page content end to end", "readme_summary": "Digital marketing agent handling brief, trend research, drafts with rule checks, human approval, scheduling and reports from dashboard. Uses Muse Wonder as main LLM with Muse Spark utility and Baseten open-weights route.", "tech_highlights": [ "Muse Wonder", "Muse Spark Open", "Approval Workflow" ], "created_at": "2026-11-01T16:34:35Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 54, "commits_before_window": 0, "prs_total": 12, "prs_merged": 6, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": true, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": true, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.5, "score_meta_tooling": 2.3, "score_tech_depth": 1.9, "score_demo": 0.8, "score_total": 6.5, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ], [ "Open-weights / fine-tuning", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (54)", "+0.6" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Automated CI workflow", "+0.2" ], [ "PR review workflow (6 PRs)", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ] ] }, "rank": 184, "is_new": true, "commits_delta": 54, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "varunchari/homeTwin", "html_url": "https://github.com/varunchari/homeTwin", "track": "Push the Frontier", "domain": "Robotics, IoT & Manufacturing", "summary": "Turns a room photo into a controllable virtual home linked to Home Assistant", "readme_summary": "Spatial studio turning room photo into masked devices and automatable virtual home. Backend compiler authors automations with Muse Spark, SAM for masks, real Home Assistant execution. Docker with Caddy, frontend and backend.", "tech_highlights": [ "SAM Masks", "Muse Spark", "Home Assistant API" ], "created_at": "2026-10-26T22:26:18Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 51, "commits_before_window": 0, "prs_total": 4, "prs_merged": 4, "is_preexisting": false, "has_docker": true, "has_tests": true, "has_src": true, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.7, "score_meta_tooling": 1.1, "score_tech_depth": 1.7, "score_demo": 1.0, "score_total": 6.5, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "High-impact domain", "+0.4" ], [ "Docker packaging", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (51)", "+0.6" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "PR review workflow (4 PRs)", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 185, "is_new": false, "commits_delta": 40, "rank_delta": 105, "commits_delta_last_run": 0 }, { "full_name": "techafreshh/qed", "html_url": "https://github.com/techafreshh/qed", "track": "Push the Frontier", "domain": "Education & Knowledge Systems", "summary": "Independent agent re-analyzes papers to deliver replicated or not verdicts", "readme_summary": "QED takes a claim plus replication package, writes fresh analysis code without running authors code, executes in Modal sandboxes. Python FastAPI orchestrator, pluggable codegen. Uses Llama Meta API and Muse Code.", "tech_highlights": [ "Llama Meta API", "Muse Code agent", "FastAPI + Modal" ], "created_at": "2026-10-28T18:41:59Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 33, "commits_before_window": 0, "prs_total": 30, "prs_merged": 30, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": true, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": true, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.5, "score_meta_tooling": 1.3, "score_tech_depth": 1.9, "score_demo": 0.8, "score_total": 6.5, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "Domain alignment", "+0.3" ], [ "Eval & benchmark proof", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (33)", "+0.4" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Agent / eval harness", "+0.2" ], [ "Automated CI workflow", "+0.2" ], [ "PR review workflow (30 PRs)", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ] ] }, "rank": 186, "is_new": false, "commits_delta": 1, "rank_delta": -68, "commits_delta_last_run": 0 }, { "full_name": "suryafk/scenefork", "html_url": "https://github.com/suryafk/scenefork", "track": "Build for Your World", "domain": "Multimodal Vision & Video (SAM / Vision)", "summary": "Pauses video to extract objects as physics bodies you can throw and command", "readme_summary": "Pauses any clip, segments clicked objects into physical bodies with mass and inpainted background. Converts voice commands like moon gravity into tested simulation programs. Built on Meta Model API with backend/frontend and evals.", "tech_highlights": [ "SAM Segmentation", "Meta Model API", "Physics Sim + Voice" ], "created_at": "2026-10-27T16:42:50Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 29, "commits_before_window": 0, "prs_total": 2, "prs_merged": 2, "is_preexisting": false, "has_docker": true, "has_tests": false, "has_src": true, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": true, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.5, "score_meta_tooling": 1.8, "score_tech_depth": 1.2, "score_demo": 1.0, "score_total": 6.5, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Eval & benchmark proof", "+0.3" ], [ "Docker packaging", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (29)", "+0.4" ], [ "Modular src/ architecture", "+0.3" ], [ "Agent / eval harness", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 187, "is_new": false, "commits_delta": 11, "rank_delta": 29, "commits_delta_last_run": 0 }, { "full_name": "kbns2000/falsify", "html_url": "https://github.com/kbns2000/falsify", "track": "Build for Your World", "domain": "Finance, Crypto & Web3", "summary": "AI devil's advocate that stress-tests market beliefs on history", "readme_summary": "Turns plain-language beliefs into sealed testable rules, replays on historical candles with deterministic engine and attack battery. Verdict FALSIFIED/FRAGILE/SURVIVED with hash-chained ledger. Explained by Muse Glimmer 30B in source language.", "tech_highlights": [ "Muse Glimmer 30B", "Hash-Chained Ledger", "Deterministic Backtest" ], "created_at": "2026-10-30T03:26:55Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 23, "commits_before_window": 0, "prs_total": 1, "prs_merged": 1, "is_preexisting": false, "has_docker": true, "has_tests": true, "has_src": true, "has_ci": true, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": true, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.2, "score_meta_tooling": 1.8, "score_tech_depth": 1.5, "score_demo": 1.0, "score_total": 6.5, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Docker packaging", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "Open-weights / fine-tuning", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (23)", "+0.4" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Automated CI workflow", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 188, "is_new": true, "commits_delta": 23, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "jaac1966/yourwine", "html_url": "https://github.com/jaac1966/yourwine", "track": "Build for Your World", "domain": "Multimodal Vision & Video (SAM / Vision)", "summary": "Glasses app that predicts if you will like a wine bottle", "readme_summary": "Android companion for Meta Adventurer glasses plus web version and API workers. Camera reads wine label, taste profile predicts personal and partner match. Built with Muse for voice-first aisle advice.", "tech_highlights": [ "Muse Models", "Smart Glasses App", "Vision + Voice" ], "created_at": "2026-10-28T02:08:55Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 20, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": true, "has_ci": false, "meta_api_verified": true, "partner_infra": "Baseten", "open_weights_tuning": true, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": true, "live_urls": [ "https://yourwine-api.jaac.workers.dev" ], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.6, "score_meta_tooling": 2.5, "score_tech_depth": 1.0, "score_demo": 1.4, "score_total": 6.5, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ], [ "Partner inference infra", "+0.2" ], [ "Open-weights / fine-tuning", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (20)", "+0.4" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Live web deployment", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 189, "is_new": true, "commits_delta": 20, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "mariovilnius/operacija-dvina", "html_url": "https://github.com/mariovilnius/operacija-dvina", "track": "Build for Your World", "domain": "Education & Knowledge Systems", "summary": "Verified audio quest and on-site missions about Lithuania's Plokstine Cold War missile base", "readme_summary": "Youth audio quest with 3 remote episodes, 7 on-site missions and 10 legend-or-fact cards about Plokstine base. Pipeline verifies every sentence against official sources and witness testimonies before publishing. Supports 11 languages with content, docs and pipeline folders.", "tech_highlights": [ "Multilingual Audio Quest", "Source Verification", "Static App + Pipeline" ], "created_at": "2026-10-26T16:28:38Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 17, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": true, "has_ci": true, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": false, "has_video_demo": true, "video_urls": [ "https://youtu.be/FxC7kLP3XLo" ], "has_live_deploy": true, "live_urls": [ "https://mariovilnius.github.io/operacija-dvina/" ], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.8, "score_meta_tooling": 1.6, "score_tech_depth": 1.2, "score_demo": 1.9, "score_total": 6.5, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (17)", "+0.4" ], [ "Modular src/ architecture", "+0.3" ], [ "Automated CI workflow", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Video walkthrough", "+1.1" ], [ "Live web deployment", "+0.4" ] ] }, "rank": 190, "is_new": true, "commits_delta": 17, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "fahad3235/sightguide", "html_url": "https://github.com/fahad3235/sightguide", "track": "Build for Your World", "domain": "Healthcare, Civic Tech & Sustainability", "summary": "Phone-first live vision and audio guidance to help blind users navigate surroundings", "readme_summary": "Captures continuous rear-camera frames for spatial vision analysis and audio navigation cues. Phone-first web app with Node.js server and Netlify serverless deployment. Built for assistive navigation with test-covered codebase.", "tech_highlights": [ "Live Vision + Audio", "Node.js + Netlify", "Mobile Web App" ], "created_at": "2026-10-26T17:24:09Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 15, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": true, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": true, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": true, "live_urls": [ "https://fahad3235.github.io/sightguide/" ], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.2, "score_meta_tooling": 1.6, "score_tech_depth": 1.7, "score_demo": 1.0, "score_total": 6.5, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "High-impact domain", "+0.4" ], [ "Eval & benchmark proof", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (15)", "+0.4" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Agent / eval harness", "+0.2" ], [ "Automated CI workflow", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Live web deployment", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 191, "is_new": false, "commits_delta": 12, "rank_delta": 104, "commits_delta_last_run": 0 }, { "full_name": "tamzid2001/sceneproof", "html_url": "https://github.com/tamzid2001/sceneproof", "track": "Push the Frontier", "domain": "Robotics, IoT & Manufacturing", "summary": "Counterfactual verifier that tests if robot world models hold after edits.", "readme_summary": "Loads object scenes or SAM 3.1 segmented images, then intervenes by moving or removing objects. Runs deterministic physics and support checks with human approval gate. Replayable proofs for embodied AI verification, Vercel demo.", "tech_highlights": [ "SAM 3.1 Vision", "World-Model Check", "FastAPI + Vercel" ], "created_at": "2026-10-27T17:13:46Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 3, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": true, "has_tests": true, "has_src": true, "has_ci": true, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": true, "live_urls": [ "https://sceneproof-ten.vercel.app" ], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.4, "score_meta_tooling": 1.8, "score_tech_depth": 1.1, "score_demo": 1.2, "score_total": 6.5, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "High-impact domain", "+0.4" ], [ "Docker packaging", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ] ], "tech": [ [ "Base", "+0.3" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Automated CI workflow", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Live web deployment", "+0.4" ] ] }, "rank": 192, "is_new": false, "commits_delta": 0, "rank_delta": -171, "commits_delta_last_run": 0 }, { "full_name": "lance2k/lusong", "html_url": "https://github.com/lance2k/lusong", "track": "Build for Your World", "domain": "Healthcare, Civic Tech & Sustainability", "summary": "Flood depth and route advice from street photos in the Philippines", "readme_summary": "Next.js app that reads flood depth from photos against MMDA gauge and combines PAGASA advisories. Built with SAM 3.1 and Muse Spark 1.3 via Meta Model API with Vercel deployment and daily quota.", "tech_highlights": [ "SAM 3.1 Vision", "Muse Spark 1.3", "Next.js + Vercel" ], "created_at": "2026-10-28T01:12:57Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 200, "commits_before_window": 0, "prs_total": 5, "prs_merged": 5, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": true, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": true, "live_urls": [ "https://lusong-mocha.vercel.app" ], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.9, "score_meta_tooling": 1.6, "score_tech_depth": 1.9, "score_demo": 1.0, "score_total": 6.4, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "High-impact domain", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (200)", "+0.6" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Automated CI workflow", "+0.2" ], [ "PR review workflow (5 PRs)", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Live web deployment", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 193, "is_new": true, "commits_delta": 200, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "hrminator/night-shift", "html_url": "https://github.com/hrminator/night-shift", "track": "Push the Frontier", "domain": "Autonomous Agents & Workflow Automation", "summary": "Overnight manager agent that acts with permissions and wakes you on evidence.", "readme_summary": "Night Shift runs simulated supplier and mail jobs overnight, acting only inside granted permissions. Built with app plus Fly.dev demo and recorded replay cases. Uses Muse Spark for reasoning and answer steps, all code written by Muse Code.", "tech_highlights": [ "Muse Spark 1.3", "Fly.io + Docker", "Permissioned Agent" ], "created_at": "2026-10-27T09:12:18Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 139, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": true, "has_tests": true, "has_src": true, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": true, "live_urls": [ "https://night-shift-demo.fly.dev/" ], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.7, "score_meta_tooling": 0.8, "score_tech_depth": 1.5, "score_demo": 1.4, "score_total": 6.4, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "High-impact domain", "+0.4" ], [ "Docker packaging", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Muse Spark integration", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (139)", "+0.6" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Live web deployment", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 194, "is_new": false, "commits_delta": 7, "rank_delta": -169, "commits_delta_last_run": 0 }, { "full_name": "rasali535/ralion-meta-hackathon", "html_url": "https://github.com/rasali535/ralion-meta-hackathon", "track": "Build for Your World", "domain": "Business, Sales & Commerce", "summary": "Growth autopilot turning business context into approved, measured actions.", "readme_summary": "MARI Growth Autopilot chains business memory to reasoning, human approval and isolated execution. Built with Next.js apps, API layer and per-tenant append-only memory with 183 tests. Uses Meta-powered reasoning with evidence receipts.", "tech_highlights": [ "Next.js + Vercel", "Meta Reasoning", "Tenant Memory" ], "created_at": "2026-10-27T15:02:20Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 89, "commits_before_window": 0, "prs_total": 10, "prs_merged": 10, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": true, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": true, "live_urls": [ "https://ralion-meta-hackathon.vercel.app" ], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.8, "score_meta_tooling": 1.3, "score_tech_depth": 1.9, "score_demo": 1.4, "score_total": 6.4, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (89)", "+0.6" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Automated CI workflow", "+0.2" ], [ "PR review workflow (10 PRs)", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Live web deployment", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 195, "is_new": false, "commits_delta": 7, "rank_delta": -114, "commits_delta_last_run": 0 }, { "full_name": "gusdom87/comfi-autopilot", "html_url": "https://github.com/gusdom87/comfi-autopilot", "track": "Build for Your World", "domain": "Business, Sales & Commerce", "summary": "Autonomous short-term rental operator gated by earned trust for each action", "readme_summary": "Coordinates guest, cleaner and mid-stay issues from reservation and cleaning calendar data. Runs on staged fixture modeled on Hospitable with graduated autonomy and evals. Built with Meta AI models for Indie Build for Your World operations.", "tech_highlights": [ "Meta AI Agents", "Graduated Autonomy", "Hospitable Fixture" ], "created_at": "2026-10-26T16:05:42Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 78, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": true, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.1, "score_meta_tooling": 1.6, "score_tech_depth": 1.7, "score_demo": 1.0, "score_total": 6.4, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Eval & benchmark proof", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (78)", "+0.6" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Agent / eval harness", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 196, "is_new": false, "commits_delta": 28, "rank_delta": -112, "commits_delta_last_run": 0 }, { "full_name": "hari431/underwriting-guideline-synthesizer", "html_url": "https://github.com/hari431/underwriting-guideline-synthesizer", "track": "Build for Your World", "domain": "Business, Sales & Commerce", "summary": "Extracts P&C insurance guideline PDFs into traceable Excel rating requirements", "readme_summary": "RateCraft extracts rating tables and routines from P&C PDFs with Muse Spark 1.3, normalizes them via deterministic validation engine, and exports Excel with evidence. Node.js 20+ only, zero runtime dependencies, one PDF per run.", "tech_highlights": [ "Muse Spark 1.3", "Node.js 20", "Excel Export" ], "created_at": "2026-10-26T09:33:55Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 51, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": true, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": true, "video_urls": [ "https://www.youtube.com/watch?v=El9TkXUMIJg", "https://youtu.be/El9TkXUMIJg" ], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.8, "score_meta_tooling": 0.8, "score_tech_depth": 1.7, "score_demo": 2.1, "score_total": 6.4, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Muse Spark integration", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (51)", "+0.6" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Automated CI workflow", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Video walkthrough", "+1.1" ], [ "Reproducible setup guide", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 197, "is_new": true, "commits_delta": 51, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "lightgo-la/symphony-meta2026-agent", "html_url": "https://github.com/lightgo-la/symphony-meta2026-agent", "track": "Push the Frontier", "domain": "Developer Tooling, Infra & Security", "summary": "Rust-native canvas to run and compare 12+ AI prompt pipelines side by side", "readme_summary": "Native Rust egui/eframe no-code canvas for orchestrating multi-step prompt pipelines concurrently. Invokes Meta muse-spark-1.3 with non-blocking async execution and live progress. Ships as Windows executable with Cargo build.", "tech_highlights": [ "Muse Spark 1.3", "Rust + egui canvas", "Concurrent pipelines" ], "created_at": "2026-10-27T12:20:38Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 46, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": true, "has_ci": true, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": false, "has_video_demo": true, "video_urls": [ "https://youtu.be/NDbVRu9LoJs" ], "has_live_deploy": true, "live_urls": [ "https://dev.meta.ai/events/global-hackathon" ], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.3, "score_meta_tooling": 0.8, "score_tech_depth": 1.2, "score_demo": 2.1, "score_total": 6.4, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "High-impact domain", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Muse Spark integration", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (46)", "+0.4" ], [ "Modular src/ architecture", "+0.3" ], [ "Automated CI workflow", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Video walkthrough", "+1.1" ], [ "Live web deployment", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 198, "is_new": false, "commits_delta": 40, "rank_delta": 230, "commits_delta_last_run": 0 }, { "full_name": "Fu93/axvigil", "html_url": "https://github.com/Fu93/axvigil", "track": "Push the Frontier", "domain": "Developer Tooling, Infra & Security", "summary": "Trains and certifies AI agents that patch smart-contract vulnerabilities", "readme_summary": "Hackathon prototype where agents solve vulnerability challenges checked by deterministic verifiers with PoC tests. Uses signed EIP-712 authorization to mint tradeable collectible and non-transferable skill record on BSC testnet. Static web demo with agent backend and contracts.", "tech_highlights": [ "Agent Verifier Harness", "EIP-712 Credentials", "Solidity + BSC Testnet" ], "created_at": "2026-10-28T20:12:27Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 41, "commits_before_window": 0, "prs_total": 10, "prs_merged": 8, "is_preexisting": false, "has_docker": true, "has_tests": true, "has_src": true, "has_ci": true, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.7, "score_meta_tooling": 1.0, "score_tech_depth": 1.7, "score_demo": 1.0, "score_total": 6.4, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "High-impact domain", "+0.4" ], [ "Docker packaging", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (41)", "+0.4" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Automated CI workflow", "+0.2" ], [ "PR review workflow (8 PRs)", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 199, "is_new": false, "commits_delta": 27, "rank_delta": -107, "commits_delta_last_run": 0 }, { "full_name": "kscooby28/META_Shop_Management", "html_url": "https://github.com/kscooby28/META_Shop_Management", "track": "Build for Your World", "domain": "Multimodal Vision & Video (SAM / Vision)", "summary": "Phone-photo car identifier for repair shops giving value, test plans and parts harvest maps", "readme_summary": "Shop AI Copilot foundation plus DIY Garage flow: photo in, car identified, harvest masks, A/B/C verdicts and listing draft. Python scaffold with SAM image evals and voice evals. Uses Meta vision and AI models with source-cited claims and Approve gate.", "tech_highlights": [ "SAM Vision Masks", "Meta AI Copilot", "Python + Eval Harness" ], "created_at": "2026-10-26T20:39:13Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 39, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": true, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.8, "score_meta_tooling": 2.3, "score_tech_depth": 1.3, "score_demo": 1.0, "score_total": 6.4, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ], [ "Open-weights / fine-tuning", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (39)", "+0.4" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 200, "is_new": false, "commits_delta": 14, "rank_delta": -93, "commits_delta_last_run": 1 }, { "full_name": "az30667176-sudo/owl", "html_url": "https://github.com/az30667176-sudo/owl", "track": "Build for Your World", "domain": "Healthcare, Civic Tech & Sustainability", "summary": "Evidence-anchored graph of US House members\u2019 stances on every issue with quotes", "readme_summary": "Civic knowledge graph mapping representatives on a -1 to +1 spectrum per issue with verbatim quotes and sources. Muse Spark extracts stances and writes cited summaries across monorepo apps and services.", "tech_highlights": [ "Muse Spark", "Knowledge Graph", "GitHub Pages" ], "created_at": "2026-10-27T05:34:33Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 34, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": true, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": true, "live_urls": [ "https://az30667176-sudo.github.io/owl/" ], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.9, "score_meta_tooling": 1.8, "score_tech_depth": 1.5, "score_demo": 1.2, "score_total": 6.4, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "High-impact domain", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (34)", "+0.4" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Automated CI workflow", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Live web deployment", "+0.4" ] ] }, "rank": 201, "is_new": false, "commits_delta": 7, "rank_delta": -82, "commits_delta_last_run": 0 }, { "full_name": "kiltro-dev/evidence-platform", "html_url": "https://github.com/kiltro-dev/evidence-platform", "track": "Push the Frontier", "domain": "Autonomous Agents & Workflow Automation", "summary": "Live agent newsroom that transcribes video and fact-checks claims as they play", "readme_summary": "Atlas Live in live/ transcribes speech, extracts checkable claims, investigates with parallel Muse agents over web and deterministic checks, publishes verdict cards over WebSocket. Python with MCP server, evals and slide-vision mismatch detection.", "tech_highlights": [ "Muse Agents", "Real-time Transcription", "WebSocket + MCP" ], "created_at": "2026-10-31T19:29:19Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 34, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": true, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.6, "score_meta_tooling": 1.3, "score_tech_depth": 1.5, "score_demo": 1.0, "score_total": 6.4, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "High-impact domain", "+0.4" ], [ "Eval & benchmark proof", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (34)", "+0.4" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Agent / eval harness", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 202, "is_new": true, "commits_delta": 34, "rank_delta": 0, "commits_delta_last_run": 22 }, { "full_name": "shittuquoyum-ui/LUCID", "html_url": "https://github.com/shittuquoyum-ui/LUCID", "track": "Push the Frontier", "domain": "Developer Tooling, Infra & Security", "summary": "Scans code commits for database leak risks and proves exploits in a sandbox", "readme_summary": "VS Code extension for AI-assisted coders that flags risky DB rule changes with warning cards and lessons. Rebuilds DB setup in disposable sandbox with fake users to prove leaks. Uses LLMs to explain risk, affected lines, pasteable fixes and A/B/C checks.", "tech_highlights": [ "VS Code Extension", "Sandbox Exploit Proof", "Supabase / Firebase" ], "created_at": "2026-10-29T03:58:49Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 27, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": true, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.3, "score_meta_tooling": 1.8, "score_tech_depth": 1.3, "score_demo": 1.0, "score_total": 6.4, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "High-impact domain", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "Open-weights / fine-tuning", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (27)", "+0.4" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 203, "is_new": true, "commits_delta": 27, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "hyper07/meta-hackathon-2026", "html_url": "https://github.com/hyper07/meta-hackathon-2026", "track": "Build for Your World", "domain": "Healthcare, Civic Tech & Sustainability", "summary": "Voice-activated safety assistant that alerts and records when you say Watch me.", "readme_summary": "Watch Me app with web server and iOS/Android clients for harassment safety. Voice trigger starts monitoring, owner-only deactivation, stranger refusal logic and incident review with pattern detection.", "tech_highlights": [ "Voice Activation", "iOS + Android", "Node Web App" ], "created_at": "2026-10-31T19:06:14Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 14, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": true, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": true, "video_urls": [ "https://github.com/hyper07/meta-hackathon-2026/raw/main/demo/watch-me-demo.mp4" ], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.9, "score_meta_tooling": 1.6, "score_tech_depth": 0.8, "score_demo": 2.1, "score_total": 6.4, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "High-impact domain", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "5+ window commits (14)", "+0.2" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Video walkthrough", "+1.1" ], [ "Reproducible setup guide", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 204, "is_new": true, "commits_delta": 14, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "vmirchev/petsafe-plants", "html_url": "https://github.com/vmirchev/petsafe-plants", "track": "Build for Your World", "domain": "Multimodal Vision & Video (SAM / Vision)", "summary": "Identifies houseplants from photos and flags pet toxicity risks with uncertainty", "readme_summary": "PetSafe Plants helps pet owners photograph plants to identify species and detect toxicity risks like lilies. It combines specialized vision models with Meta multimodal models for identification and uncertainty handling, currently in dataset and evaluation stage.", "tech_highlights": [ "Multimodal Vision AI", "Plant Classifier", "Toxicity Detection" ], "created_at": "2026-10-26T21:28:42Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 11, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": true, "has_tests": true, "has_src": true, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": true, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.5, "score_meta_tooling": 1.6, "score_tech_depth": 1.3, "score_demo": 1.0, "score_total": 6.4, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Eval & benchmark proof", "+0.3" ], [ "Docker packaging", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "5+ window commits (11)", "+0.2" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Agent / eval harness", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 205, "is_new": false, "commits_delta": 8, "rank_delta": -94, "commits_delta_last_run": 0 }, { "full_name": "smpark00/seismorescue", "html_url": "https://github.com/smpark00/seismorescue", "track": "Push the Frontier", "domain": "Multimodal Vision & Video (SAM / Vision)", "summary": "Recovers earthquake waveforms from tangled analog seismogram films", "readme_summary": "Fine-tunes Meta SAM 2.1 to trace seismic lines through crossings on synthetic WWSSN films with exact ground truth. Adds lightweight row-anchor extractor and paired real evaluation. Includes benchmarks, scripts and multi-agent runs.", "tech_highlights": [ "SAM 2.1 Fine-tuned", "Synthetic Benchmark", "Trace Extractor" ], "created_at": "2026-10-27T13:54:36Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 6, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": true, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": true, "has_eval_benchmarks": true, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.5, "score_meta_tooling": 2.3, "score_tech_depth": 1.0, "score_demo": 0.6, "score_total": 6.4, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "Domain alignment", "+0.3" ], [ "Eval & benchmark proof", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ], [ "Open-weights / fine-tuning", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "5+ window commits (6)", "+0.2" ], [ "Modular src/ architecture", "+0.3" ], [ "Agent / eval harness", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 206, "is_new": false, "commits_delta": 0, "rank_delta": -161, "commits_delta_last_run": 0 }, { "full_name": "taidang26/hoi-sau-studio", "html_url": "https://github.com/taidang26/hoi-sau-studio", "track": "Build for Your World", "domain": "Gaming, Entertainment & Creative Media", "summary": "Daily AI office-comedy comic where comments decide the next episode", "readme_summary": "Hoi Sau runs AI characters in a Vietnamese office-comedy published to Facebook, Instagram and Threads. Muse models write, draw and check episodes; audience comments drive the next chapter. Firebase/Docker pipeline with studio and architecture docs.", "tech_highlights": [ "Muse Models", "Multichannel Publishing", "Firebase + Docker" ], "created_at": "2026-10-27T02:47:18Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 167, "commits_before_window": 0, "prs_total": 65, "prs_merged": 62, "is_preexisting": false, "has_docker": true, "has_tests": false, "has_src": true, "has_ci": true, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.1, "score_meta_tooling": 1.6, "score_tech_depth": 1.6, "score_demo": 1.0, "score_total": 6.3, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "General domain", "+0.2" ], [ "Docker packaging", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (167)", "+0.6" ], [ "Modular src/ architecture", "+0.3" ], [ "Automated CI workflow", "+0.2" ], [ "PR review workflow (62 PRs)", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 207, "is_new": false, "commits_delta": 93, "rank_delta": -106, "commits_delta_last_run": 0 }, { "full_name": "Mesililm-LLC/Trackdub-Director", "html_url": "https://github.com/Mesililm-LLC/Trackdub-Director", "track": "Build for Your World", "domain": "Voice, Speech & Audio AI", "summary": "Dubbing workbench that gates timing, meaning and on-screen text verification", "readme_summary": "Trackdub Director adds verification gates between dubbing stages for timing, translation and sign localization. Built as .NET standalone app with provenance and token cost per verdict. Uses Meta Model API for translation and vision checks.", "tech_highlights": [ "Meta Model API", ".NET Workbench", "Verification Gates" ], "created_at": "2026-10-27T00:09:45Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 143, "commits_before_window": 0, "prs_total": 20, "prs_merged": 18, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": true, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.8, "score_meta_tooling": 1.6, "score_tech_depth": 1.9, "score_demo": 1.0, "score_total": 6.3, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (143)", "+0.6" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Automated CI workflow", "+0.2" ], [ "PR review workflow (18 PRs)", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 208, "is_new": false, "commits_delta": 104, "rank_delta": -156, "commits_delta_last_run": 0 }, { "full_name": "MesilimLLC/Trackdub-Director", "html_url": "https://github.com/MesilimLLC/Trackdub-Director", "track": "Build for Your World", "domain": "Voice, Speech & Audio AI", "summary": "Dubbing workbench that gates timing, meaning and on-screen text verification", "readme_summary": "Trackdub Director adds verification gates between dubbing stages for timing, translation and sign localization. Built as .NET standalone app with provenance and token cost per verdict. Uses Meta Model API for translation and vision checks.", "tech_highlights": [ "Meta Model API", ".NET Workbench", "Verification Gates" ], "created_at": "2026-10-27T00:09:45Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 143, "commits_before_window": 0, "prs_total": 20, "prs_merged": 18, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": true, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.8, "score_meta_tooling": 1.6, "score_tech_depth": 1.9, "score_demo": 1.0, "score_total": 6.3, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (143)", "+0.6" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Automated CI workflow", "+0.2" ], [ "PR review workflow (18 PRs)", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 209, "is_new": true, "commits_delta": 143, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "YanlongLai/market-claim-verifier", "html_url": "https://github.com/YanlongLai/market-claim-verifier", "track": "Build for Your World", "domain": "Finance, Crypto & Web3", "summary": "Verifies financial claims against SEC EDGAR filings with code-checked math.", "readme_summary": "Extracts claims from equity research, retrieves EDGAR evidence and checks numbers in Python with quotes and calculations preserved. Local CLI plus web explorer for saved reviews. Uses Muse Spark for extraction and review with program verification.", "tech_highlights": [ "Muse Spark 1.3", "SEC EDGAR + Python", "CLI + Explorer" ], "created_at": "2026-10-27T21:28:57Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 136, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": true, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": true, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": true, "live_urls": [ "https://hackathon.dappgo.com/" ], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.1, "score_meta_tooling": 1.3, "score_tech_depth": 1.9, "score_demo": 1.0, "score_total": 6.3, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Eval & benchmark proof", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (136)", "+0.6" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Agent / eval harness", "+0.2" ], [ "Automated CI workflow", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Live web deployment", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 210, "is_new": false, "commits_delta": 87, "rank_delta": -108, "commits_delta_last_run": 0 }, { "full_name": "debarbanson/the-witness", "html_url": "https://github.com/debarbanson/the-witness", "track": "Build for Your World", "domain": "Gaming, Entertainment & Creative Media", "summary": "Turns one photo of historic object into sourced 30s first-person film", "readme_summary": "Pipeline identifies object via OpenStreetMap/Wikidata, researches web history, verifies claims against sources, then generates era images and narration. Outputs vertical 30-37s video ending on user photo. Uses Meta models plus Modal, probe and eval harness.", "tech_highlights": [ "Muse Models", "Wikidata + OSM", "Modal + Python" ], "created_at": "2026-10-26T16:42:11Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 114, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": true, "has_eval_benchmarks": true, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.0, "score_meta_tooling": 1.8, "score_tech_depth": 1.7, "score_demo": 0.8, "score_total": 6.3, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "General domain", "+0.2" ], [ "Eval & benchmark proof", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ], [ "Open-weights / fine-tuning", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (114)", "+0.6" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Agent / eval harness", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ] ] }, "rank": 211, "is_new": false, "commits_delta": 70, "rank_delta": 103, "commits_delta_last_run": 0 }, { "full_name": "paulmalik431-ctrl/proof-of-planet", "html_url": "https://github.com/paulmalik431-ctrl/proof-of-planet", "track": "Build for Your World", "domain": "Healthcare, Civic Tech & Sustainability", "summary": "WhatsApp climate app that mints ECOIN for verified recycling actions", "readme_summary": "ECO Proof of Planet runs waste-to-value economy on WhatsApp where Meta AI verifies evidence and rules mint ECOIN. Includes web Atlas, public ledger, Supabase and Deno stack with evals and Ghost Audit for verifiability.", "tech_highlights": [ "Meta AI Vision", "WhatsApp + Supabase", "Deno + Web" ], "created_at": "2026-10-28T08:01:38Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 74, "commits_before_window": 0, "prs_total": 13, "prs_merged": 12, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": true, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": true, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": true, "live_urls": [ "https://paulmalik431-ctrl.github.io/proof-of-planet/", "https://paulmalik431-ctrl.github.io/proof-of-planet/try.html", "https://paulmalik431-ctrl.github.io/proof-of-planet/atlas.html", "https://paulmalik431-ctrl.github.io/proof-of-planet/ledger.html" ], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.2, "score_meta_tooling": 1.1, "score_tech_depth": 2.0, "score_demo": 1.0, "score_total": 6.3, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "High-impact domain", "+0.4" ], [ "Eval & benchmark proof", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (74)", "+0.6" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Agent / eval harness", "+0.2" ], [ "Automated CI workflow", "+0.2" ], [ "PR review workflow (12 PRs)", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Live web deployment", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 212, "is_new": false, "commits_delta": 6, "rank_delta": -98, "commits_delta_last_run": 0 }, { "full_name": "aiseed-dev/fieldnotes", "html_url": "https://github.com/aiseed-dev/fieldnotes", "track": "Build for Your World", "domain": "Healthcare, Civic Tech & Sustainability", "summary": "AI field observer that reads soil, weeds and weather for natural farming", "readme_summary": "Fieldnotes pairs farmer observation with AI reading terrain, geology, weeds and weather to reduce outside inputs. Built for Build for Your World with Python package, sample fields and docs. Uses Meta AI for per-field guidance.", "tech_highlights": [ "Meta AI", "Python Package", "Agri Sustainability" ], "created_at": "2026-10-28T01:33:20Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 72, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": true, "has_eval_benchmarks": false, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 1, "score_impact": 1.9, "score_meta_tooling": 2.3, "score_tech_depth": 1.5, "score_demo": 0.6, "score_total": 6.3, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "High-impact domain", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ], [ "Open-weights / fine-tuning", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (72)", "+0.6" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 213, "is_new": true, "commits_delta": 72, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "markobonna/bottega", "html_url": "https://github.com/markobonna/bottega", "track": "Build for Your World", "domain": "Business, Sales & Commerce", "summary": "Turns plain-language needs into working apps or hardware order packs.", "readme_summary": "Bottega uses Muse Spark to design Zod-validated JSON app specs rendered by a safe runtime, no arbitrary code. Supports iterative teach-and-grow edits and generates RFQ packs with CAD for hardware builds.", "tech_highlights": [ "Muse Spark", "Zod-Validated Specs", "Next.js Runtime" ], "created_at": "2026-10-26T18:09:54Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 59, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": true, "live_urls": [ "https://bottega-flame.vercel.app" ], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.8, "score_meta_tooling": 1.8, "score_tech_depth": 1.5, "score_demo": 1.2, "score_total": 6.3, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (59)", "+0.6" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Live web deployment", "+0.4" ] ] }, "rank": 214, "is_new": false, "commits_delta": 22, "rank_delta": 142, "commits_delta_last_run": 1 }, { "full_name": "phybuilds/WildScore", "html_url": "https://github.com/phybuilds/WildScore", "track": "Build for Your World", "domain": "Multimodal Vision & Video (SAM / Vision)", "summary": "Turns wildlife clips into an evidence-linked timeline with listenable event cues", "readme_summary": "Analyzes short wildlife videos into reviewable tracks and events with spatial audio cues. Built with Meta SAM 3.1 and Muse Spark 1.3, live demo is cached replay. Supports accept/reject review and CSV export of ledger.", "tech_highlights": [ "SAM 3.1 Vision", "Muse Spark 1.3", "Web + Node.js" ], "created_at": "2026-10-26T20:52:48Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 58, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": true, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": true, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": true, "live_urls": [ "https://wildscore-demo.pages.dev/" ], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.9, "score_meta_tooling": 1.6, "score_tech_depth": 1.4, "score_demo": 1.4, "score_total": 6.3, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Eval & benchmark proof", "+0.3" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (58)", "+0.6" ], [ "Modular src/ architecture", "+0.3" ], [ "Agent / eval harness", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Live web deployment", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 215, "is_new": false, "commits_delta": 25, "rank_delta": 101, "commits_delta_last_run": 0 }, { "full_name": "princetiwari1910/AuditLens", "html_url": "https://github.com/princetiwari1910/AuditLens", "track": "Build for Your World", "domain": "Multimodal Vision & Video (SAM / Vision)", "summary": "Turns phone walkthrough video into evidence-linked safety audit reports", "readme_summary": "Upload walkthrough video or photos, pick a safety checklist, get report with bounding-box overlays, clearance measurements and fixes. Uses SAM 3.1 for segmentation and Muse Spark reasoning. FastAPI + React frontend.", "tech_highlights": [ "SAM 3.1 Vision", "Muse Spark", "FastAPI + React" ], "created_at": "2026-11-01T09:33:07Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 49, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": true, "has_tests": false, "has_src": true, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": true, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.5, "score_meta_tooling": 1.6, "score_tech_depth": 1.2, "score_demo": 1.0, "score_total": 6.3, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Eval & benchmark proof", "+0.3" ], [ "Docker packaging", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (49)", "+0.4" ], [ "Modular src/ architecture", "+0.3" ], [ "Agent / eval harness", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 216, "is_new": true, "commits_delta": 49, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "cabetan/camtoshop", "html_url": "https://github.com/cabetan/camtoshop", "track": "Build for Your World", "domain": "Business, Sales & Commerce", "summary": "Turns WhatsApp product photos into ready-to-publish Reels and shop posts", "readme_summary": "Merchant sends 1-8 photos or voice note via WhatsApp, agent returns Reel with Publish/Change/Discard to post to Instagram. Portal links Instagram, Facebook Page and Shopify. Built with Muse Spark, SAM 3.1 and Muse Image.", "tech_highlights": [ "Muse Spark", "SAM 3.1 Vision", "Muse Image" ], "created_at": "2026-10-29T12:04:00Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 48, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": true, "has_tests": true, "has_src": true, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.2, "score_meta_tooling": 1.8, "score_tech_depth": 1.3, "score_demo": 1.0, "score_total": 6.3, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Docker packaging", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (48)", "+0.4" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 217, "is_new": true, "commits_delta": 48, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "gws-builds/show-me-the-problem", "html_url": "https://github.com/gws-builds/show-me-the-problem", "track": "Build for Your World", "domain": "Multimodal Vision & Video (SAM / Vision)", "summary": "Live video call agent that guides phone camera to diagnose home repair issues", "readme_summary": "Live-call agent for trades where homeowner points camera at fault. Uses Muse Spark 1.3, SAM 3.1 and Muse Voice Transcribe for guidance, hazard detection and booking. Shows safety checks, part labels and cited evidence.", "tech_highlights": [ "SAM 3.1 Vision", "Muse Spark 1.3", "Voice Transcribe" ], "created_at": "2026-10-29T16:50:41Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 38, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": true, "has_tests": true, "has_src": true, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": true, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.5, "score_meta_tooling": 1.3, "score_tech_depth": 1.5, "score_demo": 1.0, "score_total": 6.3, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Eval & benchmark proof", "+0.3" ], [ "Docker packaging", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (38)", "+0.4" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Agent / eval harness", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 218, "is_new": true, "commits_delta": 38, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "carloshurtado-tech/muse_live", "html_url": "https://github.com/carloshurtado-tech/muse_live", "track": "Build for Your World", "domain": "Gaming, Entertainment & Creative Media", "summary": "Safety net for live broadcasts with AI fixes and human approval", "readme_summary": "Operations safety net for live broadcast that plans shows, flags cross-module risk and proposes fixes with receipts. Muse proposes, human decides. Static web app with evals and live demo on Cloudflare Pages.", "tech_highlights": [ "Muse Models", "Human-in-loop", "Cloudflare Pages" ], "created_at": "2026-10-17T13:58:50Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 38, "commits_before_window": 32, "prs_total": 0, "prs_merged": 0, "is_preexisting": true, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": true, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": true, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": true, "live_urls": [ "https://muse-live.pages.dev", "https://muse-live.pages.dev/about", "https://muse-live.pages.dev/glasses/", "https://muse-live.pages.dev/about#hackathon" ], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.0, "score_meta_tooling": 1.6, "score_tech_depth": 1.7, "score_demo": 1.0, "score_total": 6.3, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "General domain", "+0.2" ], [ "Eval & benchmark proof", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (38)", "+0.4" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Agent / eval harness", "+0.2" ], [ "Automated CI workflow", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Live web deployment", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 219, "is_new": true, "commits_delta": 38, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "jcamiloaa/gridxray", "html_url": "https://github.com/jcamiloaa/gridxray", "track": "Push the Frontier", "domain": "Robotics, IoT & Manufacturing", "summary": "AI investigator maps hidden utility wiring via meters, simulation, and photos", "readme_summary": "Reads existing utility meters, hypothesizes substation feeds, and tests via physics simulator. Uses field crew switch photos to reconstruct network marked measured, inferred, or uncertain. Non-AI checker scores results; built by Zynplex.", "tech_highlights": [ "Muse Models", "Physics Simulator", "SAM Vision" ], "created_at": "2026-10-27T14:12:21Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 37, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": true, "has_tests": false, "has_src": true, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.5, "score_meta_tooling": 1.8, "score_tech_depth": 1.0, "score_demo": 1.0, "score_total": 6.3, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "High-impact domain", "+0.4" ], [ "Docker packaging", "+0.4" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (37)", "+0.4" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 220, "is_new": true, "commits_delta": 37, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "kopias/pimp-my-social", "html_url": "https://github.com/kopias/pimp-my-social", "track": "Build for Your World", "domain": "Business, Sales & Commerce", "summary": "Rebuilds small business sites for search, AI agents and branding", "readme_summary": "Takes a business URL, Instagram and shop to score discoverability then rebuilds an editorial site, studio photos, campaign and brand skill. Python pipeline using five Meta models including Muse Spark and SAM. Demo showroom with deploy scripts.", "tech_highlights": [ "Muse Spark 1.3", "Meta Vision Models", "Python Pipeline" ], "created_at": "2026-10-26T16:16:56Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 36, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": true, "live_urls": [ "https://pimpmysocial.loreto.io" ], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.8, "score_meta_tooling": 1.8, "score_tech_depth": 1.3, "score_demo": 1.4, "score_total": 6.3, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (36)", "+0.4" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Live web deployment", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 221, "is_new": true, "commits_delta": 36, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "cristianuibar/learnquiz", "html_url": "https://github.com/cristianuibar/learnquiz", "track": "Build for Your World", "domain": "Education & Knowledge Systems", "summary": "Adaptive quiz app that turns any topic into a leveled spaced-repetition curriculum", "readme_summary": "Personalized learning app with placement quiz, retrieval practice and difficulty adaptation. Uses Muse Spark 1.3 for curriculum and questions, with planned Wonder, Image and Voice models, built on Cloudflare stack.", "tech_highlights": [ "Muse Spark 1.3", "Drizzle + Cloudflare", "Next.js App" ], "created_at": "2026-10-27T16:55:22Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 34, "commits_before_window": 0, "prs_total": 18, "prs_merged": 15, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": true, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": true, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.5, "score_meta_tooling": 2.3, "score_tech_depth": 1.7, "score_demo": 0.8, "score_total": 6.3, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ], [ "Open-weights / fine-tuning", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (34)", "+0.4" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Automated CI workflow", "+0.2" ], [ "PR review workflow (15 PRs)", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ] ] }, "rank": 222, "is_new": true, "commits_delta": 34, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "vumoz/convoplex-retention-agent", "html_url": "https://github.com/vumoz/convoplex-retention-agent", "track": "Build for Your World", "domain": "Business, Sales & Commerce", "summary": "WhatsApp win-back agent helping Nigerian shops re-engage quiet customers", "readme_summary": "WhatsApp retention agent for Nigerian retailers to send naira-priced offers. Customers reply by text or voice note in their language. Built with Muse Spark for text, Muse Image for pictures and voice transcription.", "tech_highlights": [ "Muse Spark 1.3", "Muse Image 1.0", "WhatsApp + FastAPI" ], "created_at": "2026-10-27T06:28:53Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 31, "commits_before_window": 0, "prs_total": 31, "prs_merged": 31, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": true, "live_urls": [ "https://convoplex-retention-agent.vercel.app/", "https://convoplex-retention-agent.vercel.app/demo", "https://convoplex-retention-agent.vercel.app" ], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.8, "score_meta_tooling": 1.6, "score_tech_depth": 1.5, "score_demo": 1.4, "score_total": 6.3, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (31)", "+0.4" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "PR review workflow (31 PRs)", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Live web deployment", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 223, "is_new": false, "commits_delta": 16, "rank_delta": -114, "commits_delta_last_run": 0 }, { "full_name": "dobald/monster-in-the-closet", "html_url": "https://github.com/dobald/monster-in-the-closet", "track": "Build for Your World", "domain": "Multimodal Vision & Video (SAM / Vision)", "summary": "Morning outfit agent that catalogs closet photos and styles forgotten clothes", "readme_summary": "Flat-lay photos are segmented then catalogued, then a daily agent picks weather- and calendar-aware outfits. Python server with Docker/Fly config and test fixtures. Uses SAM 3.1 for garment cutout and Muse Spark for cataloging and styling.", "tech_highlights": [ "SAM 3.1 Vision", "Muse Spark", "Python Server" ], "created_at": "2026-10-26T17:58:44Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 28, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": true, "has_tests": true, "has_src": true, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": true, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.2, "score_meta_tooling": 1.8, "score_tech_depth": 1.3, "score_demo": 1.0, "score_total": 6.3, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Docker packaging", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ], [ "Open-weights / fine-tuning", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (28)", "+0.4" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 224, "is_new": false, "commits_delta": 6, "rank_delta": -92, "commits_delta_last_run": 0 }, { "full_name": "arifiarber-sYn/halim-fatura-agent", "html_url": "https://github.com/arifiarber-sYn/halim-fatura-agent", "track": "Build for Your World", "domain": "Healthcare, Civic Tech & Sustainability", "summary": "Procurement agent that acts on public data and returns hash-chained receipts.", "readme_summary": "Three-layer agent turns requests into intents, runs SQL tools over Kosovo OCDS procurement data with audit and policy checks. Every answer includes an immutable hash-chained receipt with verification endpoint. Uses Meta Model API for understanding with measured docs.", "tech_highlights": [ "Meta Model API", "SQL + OCDS Data", "Hash-Chain Receipts" ], "created_at": "2026-10-26T16:33:53Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 28, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": true, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": true, "video_urls": [ "https://cdn.jsdelivr.net/gh/arifiarber-sYn/halim-fatura-agent@master/demo-halimi-178s.mp4", "https://cdn.jsdelivr.net/gh/arifiarber-sYn/halim-fatura-agent@master/demo-halimi-en.mp4" ], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.6, "score_meta_tooling": 1.3, "score_tech_depth": 1.5, "score_demo": 1.9, "score_total": 6.3, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "High-impact domain", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (28)", "+0.4" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Automated CI workflow", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Video walkthrough", "+1.1" ], [ "Reproducible setup guide", "+0.4" ] ] }, "rank": 225, "is_new": false, "commits_delta": 7, "rank_delta": -11, "commits_delta_last_run": 0 }, { "full_name": "RussCTGL/hiddenlot", "html_url": "https://github.com/RussCTGL/hiddenlot", "track": "Build for Your World", "domain": "Robotics, IoT & Manufacturing", "summary": "Search tool surfacing shareable surplus steel lots with evidence trails", "readme_summary": "Discovers surplus hot-rolled coil and remainders across consenting trade networks. Demo with synthetic users in Haiphong and Houston shows evidence-backed lots. Built during hackathon with daily-reset demo and synthetic data only.", "tech_highlights": [ "Trade Network Search", "Evidence-backed UI", "Vercel + Docker" ], "created_at": "2026-10-28T00:31:06Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 28, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": true, "has_tests": true, "has_src": true, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": true, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": true, "live_urls": [ "https://hiddenlot-nine.vercel.app" ], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.6, "score_meta_tooling": 0.8, "score_tech_depth": 1.5, "score_demo": 1.4, "score_total": 6.3, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "High-impact domain", "+0.4" ], [ "Eval & benchmark proof", "+0.3" ], [ "Docker packaging", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Muse Spark integration", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (28)", "+0.4" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Agent / eval harness", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Live web deployment", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 226, "is_new": false, "commits_delta": 8, "rank_delta": -104, "commits_delta_last_run": 0 }, { "full_name": "gowtham472/handoffproof", "html_url": "https://github.com/gowtham472/handoffproof", "track": "Push the Frontier", "domain": "Developer Tooling, Infra & Security", "summary": "Docker-based drill that rehearses developer exits and diagnoses handover gaps.", "readme_summary": "Go controller runs developer-exit drills in isolated Docker Compose sandboxes, withdrawing credentials and testing recovery. Meta Muse Spark 1.3 agent diagnoses from verified evidence. Supports Bring Your Own App onboarding.", "tech_highlights": [ "Muse Spark 1.3", "Go + Docker Compose", "Exit-Drill Harness" ], "created_at": "2026-11-01T14:18:15Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 27, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": true, "has_ci": true, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": true, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.6, "score_meta_tooling": 1.3, "score_tech_depth": 1.4, "score_demo": 1.0, "score_total": 6.3, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "High-impact domain", "+0.4" ], [ "Eval & benchmark proof", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (27)", "+0.4" ], [ "Modular src/ architecture", "+0.3" ], [ "Agent / eval harness", "+0.2" ], [ "Automated CI workflow", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 227, "is_new": true, "commits_delta": 27, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "rajkumar-prog/who-judges-the-judge", "html_url": "https://github.com/rajkumar-prog/who-judges-the-judge", "track": "Push the Frontier", "domain": "Developer Tooling, Infra & Security", "summary": "Tests AI code judges against an adapting cheater using hidden tests as answer key", "readme_summary": "Local harness pits a Muse Spark Open judge against a cheater that hardcodes tests. Measures judge blind spots and shows counterexample prompting closes the gap. Stack is Python, pytest, dashboard with seeded open-source test subjects.", "tech_highlights": [ "Muse Spark Open", "Python + pytest", "Hidden-test harness" ], "created_at": "2026-10-26T10:59:22Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 14, "commits_before_window": 0, "prs_total": 15, "prs_merged": 13, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": true, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": true, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.3, "score_meta_tooling": 1.5, "score_tech_depth": 1.5, "score_demo": 1.0, "score_total": 6.3, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "High-impact domain", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ], [ "Open-weights / fine-tuning", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "5+ window commits (14)", "+0.2" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Automated CI workflow", "+0.2" ], [ "PR review workflow (13 PRs)", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 228, "is_new": false, "commits_delta": 8, "rank_delta": 121, "commits_delta_last_run": 0 }, { "full_name": "TsilavinaZh/RecupBuild", "html_url": "https://github.com/TsilavinaZh/RecupBuild", "track": "Build for Your World", "domain": "Healthcare, Civic Tech & Sustainability", "summary": "Turns one photo of reclaimed wood into measured build and cut plans", "readme_summary": "PHP MVC + SQLite app uses A4 sheet for scale to measure planks, generates sized projects, cut placement, 3D render and assembly steps. Live demo site with vanilla JS/CSS frontend.", "tech_highlights": [ "PHP 8.3 + SQLite", "Vision Measurement", "Cut Plan + 3D Render" ], "created_at": "2026-10-28T06:55:51Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 11, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": true, "video_urls": [ "https://youtu.be/sO_UkvMmugU", "https://www.youtube.com/watch?v=sO_UkvMmugU" ], "has_live_deploy": true, "live_urls": [ "https://recupbuild.tendry.mg/" ], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 1, "score_impact": 1.9, "score_meta_tooling": 0.8, "score_tech_depth": 1.1, "score_demo": 2.5, "score_total": 6.3, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "High-impact domain", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Muse Spark integration", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "5+ window commits (11)", "+0.2" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Video walkthrough", "+1.1" ], [ "Reproducible setup guide", "+0.4" ], [ "Live web deployment", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 229, "is_new": true, "commits_delta": 11, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "Rexangels/ForgeBot", "html_url": "https://github.com/Rexangels/ForgeBot", "track": "Push the Frontier", "domain": "Robotics, IoT & Manufacturing", "summary": "Designs robot hardware and firmware from a sketch via simulation and CAD.", "readme_summary": "Closed-loop Vision-to-Hardware studio using Muse Wonder 1.0, Muse Spark 1.3 and SAM 3.1 to reason over assemblies. Django backend, React Three.js frontend, MuJoCo physics and FreeCAD generation.", "tech_highlights": [ "Muse Wonder 1.0", "Muse Spark 1.3", "SAM 3.1 + MuJoCo" ], "created_at": "2026-10-26T16:50:37Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 10, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": true, "has_tests": false, "has_src": true, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.7, "score_meta_tooling": 1.8, "score_tech_depth": 0.8, "score_demo": 1.0, "score_total": 6.3, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "High-impact domain", "+0.4" ], [ "Docker packaging", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ] ], "tech": [ [ "Base", "+0.3" ], [ "5+ window commits (10)", "+0.2" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 230, "is_new": false, "commits_delta": 3, "rank_delta": -94, "commits_delta_last_run": 0 }, { "full_name": "waleedmustafa971/forge-0-hackathon", "html_url": "https://github.com/waleedmustafa971/forge-0-hackathon", "track": "Push the Frontier", "domain": "Developer Tooling, Infra & Security", "summary": "Debugging agent that tests hypotheses in a sandbox before proposing a patch.", "readme_summary": "Evidence-driven debugging agent that forms competing root-cause hypotheses and runs sandbox experiments. Only proposes a patch after evidence converges, requiring independent verifier approval. Built on Meta Muse Spark.", "tech_highlights": [ "Muse Spark", "Sandbox Verifier", "Hypothesis Testing" ], "created_at": "2026-10-28T04:36:13Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 9, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": false, "has_ci": true, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": true, "has_setup_guide": false, "has_video_demo": true, "video_urls": [ "https://youtu.be/DmIuamMJUTg" ], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.4, "score_meta_tooling": 1.3, "score_tech_depth": 0.9, "score_demo": 1.7, "score_total": 6.3, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "High-impact domain", "+0.4" ], [ "Eval & benchmark proof", "+0.3" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "5+ window commits (9)", "+0.2" ], [ "Agent / eval harness", "+0.2" ], [ "Automated CI workflow", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Video walkthrough", "+1.1" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 231, "is_new": false, "commits_delta": 2, "rank_delta": -33, "commits_delta_last_run": 0 }, { "full_name": "rajagavaskargithub/ASG-AI-SQL-Guard", "html_url": "https://github.com/rajagavaskargithub/ASG-AI-SQL-Guard", "track": "Push the Frontier", "domain": "Developer Tooling, Infra & Security", "summary": "Deterministic guard that allows or blocks AI-generated SQL queries", "readme_summary": "Security layer between LLM SQL and DuckDB using sqlglot parsing and policy.yaml allowlists. Enforces SELECT-only, column deny, LIMIT and human approval with audit log. Prototype with fake data, Streamlit app and redteam results.", "tech_highlights": [ "SQLGlot Policy Guard", "Streamlit + DuckDB", "LLM SQL Auditing" ], "created_at": "2026-10-29T22:01:28Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 6, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": true, "video_urls": [ "https://youtu.be/ItiS29Ggfjw" ], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.0, "score_meta_tooling": 1.3, "score_tech_depth": 1.1, "score_demo": 1.9, "score_total": 6.3, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "High-impact domain", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "5+ window commits (6)", "+0.2" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Video walkthrough", "+1.1" ], [ "Reproducible setup guide", "+0.4" ] ] }, "rank": 232, "is_new": true, "commits_delta": 6, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "mattwatson7/reality-compiler-hackathon-2026", "html_url": "https://github.com/mattwatson7/reality-compiler-hackathon-2026", "track": "Push the Frontier", "domain": "Multimodal Vision & Video (SAM / Vision)", "summary": "Compiles written procedures and verifies them against visual evidence", "readme_summary": "Compiles procedures into typed requirements and checks timestamped visual evidence with deterministic PASS/FAIL/UNKNOWN evaluator. Uses Muse Wonder 1.0 for semantic compilation and SAM 3.1 masks/tracks. FastAPI backend + frontend in Docker.", "tech_highlights": [ "Muse Wonder 1.0", "SAM 3.1 Vision", "FastAPI + Docker" ], "created_at": "2026-10-29T15:42:55Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 2, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": true, "has_tests": false, "has_src": true, "has_ci": true, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": true, "video_urls": [ "https://www.youtube.com/watch?v=H0gd17Sj3N8" ], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.3, "score_meta_tooling": 1.3, "score_tech_depth": 0.8, "score_demo": 1.9, "score_total": 6.3, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "Domain alignment", "+0.3" ], [ "Docker packaging", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ] ], "meta": [ [ "Base", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ] ], "tech": [ [ "Base", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Automated CI workflow", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Video walkthrough", "+1.1" ], [ "Reproducible setup guide", "+0.4" ] ] }, "rank": 233, "is_new": true, "commits_delta": 2, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "MackentochKelly/koblip-book", "html_url": "https://github.com/MackentochKelly/koblip-book", "track": "Build for Your World", "domain": "Business, Sales & Commerce", "summary": "One-minute booking pages for local businesses managed by typing or talking", "readme_summary": "Find business on Google Maps, share page and manage day via chat or voice. Next.js with Drizzle, docs and CI. Uses Meta AI for conversational scheduling and business setup.", "tech_highlights": [ "Muse Spark", "Next.js + Drizzle", "Voice + Chat UI" ], "created_at": "2026-10-27T01:23:25Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 689, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": true, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": true, "live_urls": [ "https://book.koblip.com" ], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.8, "score_meta_tooling": 1.3, "score_tech_depth": 1.7, "score_demo": 1.4, "score_total": 6.2, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (689)", "+0.6" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Automated CI workflow", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Live web deployment", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 234, "is_new": true, "commits_delta": 689, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "lutic1/meta-hackathon-2026", "html_url": "https://github.com/lutic1/meta-hackathon-2026", "track": "Build for Your World", "domain": "Gaming, Entertainment & Creative Media", "summary": "Turns room photos into a playable escape room run by wizard agents", "readme_summary": "Keyframe photographs a room and generates a playable escape room in minutes. Council of Muse Spark agents handles objects, puzzles, hints and difficulty, with SAM 3.1 vision, Muse Image and Voice. Local Llama 3.2 via Ollama.", "tech_highlights": [ "SAM 3.1 Vision", "Muse Spark Agents", "Muse Image + Voice" ], "created_at": "2026-10-20T17:26:58Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 417, "commits_before_window": 56, "prs_total": 2, "prs_merged": 2, "is_preexisting": true, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": true, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.7, "score_meta_tooling": 1.8, "score_tech_depth": 1.7, "score_demo": 1.0, "score_total": 6.2, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "General domain", "+0.2" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (417)", "+0.6" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Automated CI workflow", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 235, "is_new": false, "commits_delta": 62, "rank_delta": -224, "commits_delta_last_run": 0 }, { "full_name": "phaladamou/employee-platform", "html_url": "https://github.com/phaladamou/employee-platform", "track": "Push the Frontier", "domain": "Autonomous Agents & Workflow Automation", "summary": "Marketplace to recruit AI workers with persistent verifiable work identities.", "readme_summary": "Platform where creators publish locked agent DNA and employers assign missions. Agents plan and use tools in sandbox accumulating verifiable history. Full-stack app with desktop client and mission reports.", "tech_highlights": [ "Autonomous Agents", "Verifiable Identity", "Sandbox Execution" ], "created_at": "2026-10-27T03:11:47Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 252, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": true, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": true, "live_urls": [ "https://employee-platform-six.vercel.app" ], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 4, "score_impact": 2.0, "score_meta_tooling": 1.3, "score_tech_depth": 1.7, "score_demo": 1.2, "score_total": 6.2, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "High-impact domain", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (252)", "+0.6" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Automated CI workflow", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Live web deployment", "+0.4" ] ] }, "rank": 236, "is_new": false, "commits_delta": 176, "rank_delta": -95, "commits_delta_last_run": 4 }, { "full_name": "medomohamed22/admorph-ai", "html_url": "https://github.com/medomohamed22/admorph-ai", "track": "Build for Your World", "domain": "Business, Sales & Commerce", "summary": "Turns one phone photo into a dialect-correct Instagram ad in a minute", "readme_summary": "AdMorph cuts products out of phone photos, reads the brand, writes English/Arabic RTL copy, lays out sized creatives and renders and verifies the final image. Web app running only on Meta models with phone and desktop UI. Uses SAM 3.1 for segmentation, Muse Spark for copy/layout and Muse Image for painting.", "tech_highlights": [ "SAM 3.1 Vision", "Muse Spark", "Muse Image" ], "created_at": "2026-10-26T11:03:08Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 236, "commits_before_window": 0, "prs_total": 111, "prs_merged": 111, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": true, "live_urls": [ "https://admorph-ai-app.vercel.app/", "https://admorph-ai-app.vercel.app" ], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.8, "score_meta_tooling": 1.3, "score_tech_depth": 1.7, "score_demo": 1.4, "score_total": 6.2, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (236)", "+0.6" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "PR review workflow (111 PRs)", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Live web deployment", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 237, "is_new": false, "commits_delta": 102, "rank_delta": -125, "commits_delta_last_run": 0 }, { "full_name": "M4SPIDER/spider-game-engine-open-source-", "html_url": "https://github.com/M4SPIDER/spider-game-engine-open-source-", "track": "Build for Your World", "domain": "Gaming, Entertainment & Creative Media", "summary": "Agentic 3D game engine that builds and runs Three.js games in real time", "readme_summary": "React, Three.js and WebGL engine with Electron, Tauri and web support for live game synthesis. Integrates Meta Llama and Muse over MCP for voice transcribe, mounting and verification.", "tech_highlights": [ "Three.js + React", "MCP Agent Engine", "Meta Llama + Muse" ], "created_at": "2026-10-26T17:49:27Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 138, "commits_before_window": 0, "prs_total": 1, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": true, "has_ci": true, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": true, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": true, "live_urls": [ "https://m4spider.github.io/spider-game-engine-open-source-/" ], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 9, "score_impact": 2.0, "score_meta_tooling": 1.6, "score_tech_depth": 1.6, "score_demo": 1.0, "score_total": 6.2, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "General domain", "+0.2" ], [ "Eval & benchmark proof", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (138)", "+0.6" ], [ "Modular src/ architecture", "+0.3" ], [ "Agent / eval harness", "+0.2" ], [ "Automated CI workflow", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Live web deployment", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 238, "is_new": true, "commits_delta": 138, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "olamidefasogbon/mizzou", "html_url": "https://github.com/olamidefasogbon/mizzou", "track": "Build for Your World", "domain": "Education & Knowledge Systems", "summary": "Autonomous agent that turns opportunity links into verified applications", "readme_summary": "Reads official sources, FAQs and PDFs to verify deadlines, eligibility and prep plans. Built on Meta Muse models with chat UI, anonymous sessions, Google calendar sync, Supabase stack.", "tech_highlights": [ "Muse Models", "Supabase + Next.js", "Agent + Calendar" ], "created_at": "2026-10-27T15:06:18Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 137, "commits_before_window": 0, "prs_total": 6, "prs_merged": 6, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": true, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": true, "live_urls": [ "https://mizzou.vercel.app" ], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.8, "score_meta_tooling": 1.8, "score_tech_depth": 1.4, "score_demo": 1.2, "score_total": 6.2, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (137)", "+0.6" ], [ "Modular src/ architecture", "+0.3" ], [ "PR review workflow (6 PRs)", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Live web deployment", "+0.4" ] ] }, "rank": 239, "is_new": true, "commits_delta": 137, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "AIOHM/adisaan-hackathon", "html_url": "https://github.com/AIOHM/adisaan-hackathon", "track": "Build for Your World", "domain": "Healthcare, Civic Tech & Sustainability", "summary": "Human vs AI Q&A walls publishing consented labelled answers", "readme_summary": "Laravel app behind tbwim.adisaan.com collects human and AI answers separately for synthesis. Runs on Meta Model API under spending cap with tests, consented publishing flow.", "tech_highlights": [ "Meta Model API", "Laravel App", "Human-AI Data" ], "created_at": "2026-10-27T01:36:05Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 109, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": true, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.9, "score_meta_tooling": 1.6, "score_tech_depth": 1.7, "score_demo": 1.0, "score_total": 6.2, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "High-impact domain", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (109)", "+0.6" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Automated CI workflow", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 240, "is_new": true, "commits_delta": 109, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "Divyesh-Thirukonda/cruise", "html_url": "https://github.com/Divyesh-Thirukonda/cruise", "track": "Push the Frontier", "domain": "Robotics, IoT & Manufacturing", "summary": "Voice-programmable modular device that generates games and controls", "readme_summary": "Modulate lets users speak a job for modular hardware, then generates and checks on-device code. Raspberry Pi and computer targets with local execution after generation. Uses Meta agent for code generation and voice answers.", "tech_highlights": [ "Meta Agent", "Raspberry Pi", "Voice Programming" ], "created_at": "2026-10-28T03:36:29Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 77, "commits_before_window": 0, "prs_total": 2, "prs_merged": 2, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": true, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": true, "live_urls": [ "https://modulate-connect.vercel.app/connect", "https://modulate-connect.vercel.app/connect/setup", "https://dulate-connect.vercel.app" ], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.3, "score_meta_tooling": 0.8, "score_tech_depth": 1.7, "score_demo": 1.4, "score_total": 6.2, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "High-impact domain", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Muse Spark integration", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (77)", "+0.6" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Automated CI workflow", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Live web deployment", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 241, "is_new": false, "commits_delta": 21, "rank_delta": -178, "commits_delta_last_run": 0 }, { "full_name": "poferraz/vibe-fence", "html_url": "https://github.com/poferraz/vibe-fence", "track": "Push the Frontier", "domain": "Developer Tooling, Infra & Security", "summary": "Pre-commit safety fence that blocks risky AI agent actions and secret leaks", "readme_summary": "Safety companion for AI coding agents that pre-checks dangerous patterns and scans commits. Uses project router, skills and Git hooks with plain-language explanations. Built as a Meta harness for non-technical builders, not a full sandbox.", "tech_highlights": [ "Pre-commit Hooks", "Secret Scanning", "Muse Spark" ], "created_at": "2026-10-26T16:44:00Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 71, "commits_before_window": 21, "prs_total": 14, "prs_merged": 11, "is_preexisting": true, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": true, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.3, "score_meta_tooling": 1.0, "score_tech_depth": 1.9, "score_demo": 1.0, "score_total": 6.2, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "High-impact domain", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (71)", "+0.6" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Automated CI workflow", "+0.2" ], [ "PR review workflow (11 PRs)", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 242, "is_new": false, "commits_delta": 48, "rank_delta": -188, "commits_delta_last_run": 0 }, { "full_name": "vamsikrishna2421/restaurantos-ai", "html_url": "https://github.com/vamsikrishna2421/restaurantos-ai", "track": "Build for Your World", "domain": "Business, Sales & Commerce", "summary": "Multilingual voice ordering and kitchen manager for restaurants", "readme_summary": "Guests order by phone/kiosk in Telugu, Tamil, Spanish-English via Muse Voice Transcribe to cart ops. Deterministic multilingual kitchen display plus recipe inventory forecasting. Governed AI manager, Docker/Fly deployment.", "tech_highlights": [ "Muse Voice Transcribe", "Muse Spark 1.3", "Docker + Fly.io" ], "created_at": "2026-10-27T15:00:59Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 59, "commits_before_window": 0, "prs_total": 17, "prs_merged": 16, "is_preexisting": false, "has_docker": true, "has_tests": true, "has_src": true, "has_ci": true, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.9, "score_meta_tooling": 1.6, "score_tech_depth": 1.9, "score_demo": 0.8, "score_total": 6.2, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Docker packaging", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (59)", "+0.6" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Automated CI workflow", "+0.2" ], [ "PR review workflow (16 PRs)", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ] ] }, "rank": 243, "is_new": false, "commits_delta": 38, "rank_delta": -122, "commits_delta_last_run": 0 }, { "full_name": "The-Nexus-system/blind-creator-preflight", "html_url": "https://github.com/The-Nexus-system/blind-creator-preflight", "track": "Build for Your World", "domain": "Healthcare, Civic Tech & Sustainability", "summary": "Pre-publish vision check that tells blind creators if a photo or video is post-ready", "readme_summary": "Simulated Instagram composer running six checks: framing, crop safety, sharpness, text, impression and privacy. Reports pass/fix/uncertain in screen-reader and braille-readable text. Client-server app with Docker, tests and documented model choices.", "tech_highlights": [ "Vision accessibility", "Docker + Node stack", "Screen-reader UX" ], "created_at": "2026-10-28T17:41:43Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 47, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": true, "has_tests": true, "has_src": true, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.3, "score_meta_tooling": 1.8, "score_tech_depth": 1.3, "score_demo": 0.8, "score_total": 6.2, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "High-impact domain", "+0.4" ], [ "Docker packaging", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (47)", "+0.4" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ] ] }, "rank": 244, "is_new": false, "commits_delta": 36, "rank_delta": -110, "commits_delta_last_run": 0 }, { "full_name": "jin7744/tendercheck", "html_url": "https://github.com/jin7744/tendercheck", "track": "Push the Frontier", "domain": "Legal & Compliance", "summary": "Checks tender bid packages against source docs with code-verified quotes", "readme_summary": "Muse Spark finds requirements and matches bidder files, while deterministic code verifies quotes and decides status. Never declares eligibility. Includes evals, scenarios and replayable web demo.", "tech_highlights": [ "Muse Spark", "Verification Engine", "Replayable Evals" ], "created_at": "2026-11-01T11:05:21Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 44, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": false, "has_ci": true, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": true, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": true, "live_urls": [ "https://jin7744.github.io/tendercheck/" ], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.5, "score_meta_tooling": 1.3, "score_tech_depth": 1.4, "score_demo": 1.0, "score_total": 6.2, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "Domain alignment", "+0.3" ], [ "Eval & benchmark proof", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (44)", "+0.4" ], [ "Automated test suite", "+0.3" ], [ "Agent / eval harness", "+0.2" ], [ "Automated CI workflow", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Live web deployment", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 245, "is_new": true, "commits_delta": 44, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "KanishkNoir/SwitchBoard", "html_url": "https://github.com/KanishkNoir/SwitchBoard", "track": "Push the Frontier", "domain": "Developer Tooling, Infra & Security", "summary": "Mediation layer that remembers agent decisions and reduces needy interruptions", "readme_summary": "Sits between user and multiple agents to store scoped decisions and interrupt only when worthwhile. Harness with integrations and Modal app to track attention cost across workflows. Built as agent infrastructure tooling.", "tech_highlights": [ "Multi-Agent Routing", "Decision Memory Store", "Modal + Python" ], "created_at": "2026-10-28T21:08:30Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 34, "commits_before_window": 0, "prs_total": 2, "prs_merged": 2, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 2, "score_impact": 2.3, "score_meta_tooling": 1.6, "score_tech_depth": 1.3, "score_demo": 1.0, "score_total": 6.2, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "High-impact domain", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (34)", "+0.4" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 246, "is_new": true, "commits_delta": 34, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "ayoubna99/life-agent", "html_url": "https://github.com/ayoubna99/life-agent", "track": "Build for Your World", "domain": "Autonomous Agents & Workflow Automation", "summary": "Self-improving time agent that plans days and curbs doomscrolling", "readme_summary": "Android Flutter plus Kotlin app where agent Lify plans days, sets alarms and intervenes on scrolling. Uses Muse Spark, Muse Spark Open, Muse Image and Voice Transcribe with Supabase backend.", "tech_highlights": [ "Muse Spark", "Muse Image + Voice", "Flutter + Supabase" ], "created_at": "2026-10-26T17:42:35Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 31, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": true, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": true, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 1, "score_impact": 1.9, "score_meta_tooling": 1.8, "score_tech_depth": 1.5, "score_demo": 1.0, "score_total": 6.2, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "High-impact domain", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ], [ "Open-weights / fine-tuning", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (31)", "+0.4" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Automated CI workflow", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 247, "is_new": true, "commits_delta": 31, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "Looming41/pocketllm", "html_url": "https://github.com/Looming41/pocketllm", "track": "Push the Frontier", "domain": "Developer Tooling, Infra & Security", "summary": "Runs 30B-100B+ MoE models offline from USB by streaming only active experts", "readme_summary": "Portable runtime that runs large MoE models on low-RAM laptops fully offline from USB drives. Patches llama.cpp CPU MoE kernel for concurrent expert streaming plus striping and planner. Reports fit and placement before download with measured tuning.", "tech_highlights": [ "llama.cpp MoE Patch", "USB Expert Streaming", "Offline Inference" ], "created_at": "2026-10-27T12:51:07Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 27, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": true, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": true, "has_eval_benchmarks": false, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.3, "score_meta_tooling": 1.8, "score_tech_depth": 1.5, "score_demo": 0.6, "score_total": 6.2, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "High-impact domain", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "Open-weights / fine-tuning", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (27)", "+0.4" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Automated CI workflow", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 248, "is_new": true, "commits_delta": 27, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "IrwinJam/agent-cost-harness", "html_url": "https://github.com/IrwinJam/agent-cost-harness", "track": "Push the Frontier", "domain": "Developer Tooling, Infra & Security", "summary": "Cuts agent API costs 21-37% while verifying task performance holds", "readme_summary": "Harness with caching and reasoning policies plus eval suite measuring cost per run vs tasks passed. Python harness/serve CLI, Docker, eval and docs/RESULTS.md. Tested on muse-spark-1.3 with Muse API integration docs.", "tech_highlights": [ "Muse Spark 1.3", "Cost Optimization", "Agent Evaluation" ], "created_at": "2026-10-27T00:57:28Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 19, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": true, "has_tests": true, "has_src": false, "has_ci": true, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": true, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 3, "score_impact": 3.0, "score_meta_tooling": 0.8, "score_tech_depth": 1.4, "score_demo": 1.0, "score_total": 6.2, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "High-impact domain", "+0.4" ], [ "Eval & benchmark proof", "+0.3" ], [ "Docker packaging", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Muse Spark integration", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (19)", "+0.4" ], [ "Automated test suite", "+0.3" ], [ "Agent / eval harness", "+0.2" ], [ "Automated CI workflow", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 249, "is_new": true, "commits_delta": 19, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "8-BitRhyon/settleye", "html_url": "https://github.com/8-BitRhyon/settleye", "track": "Push the Frontier", "domain": "Developer Tooling, Infra & Security", "summary": "Audits support agent transcripts and flags refunds not settled in Stripe or Shopify", "readme_summary": "Backend extracts binding refund promises via meta-models/muse-spark-open-1026 with Pydantic validation. Reconciles each against Stripe/Shopify ledger state into verified/drift queue. Daemon plus explain endpoint with one-click fix.", "tech_highlights": [ "Muse Spark 1026", "FastAPI + Pydantic", "Stripe + Shopify" ], "created_at": "2026-10-26T08:36:46Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 17, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": true, "has_ci": true, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": true, "has_eval_benchmarks": true, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": true, "live_urls": [ "https://8-bitrhyon.github.io/settleye/landing.html" ], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.3, "score_meta_tooling": 1.3, "score_tech_depth": 1.4, "score_demo": 1.2, "score_total": 6.2, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "High-impact domain", "+0.4" ], [ "Eval & benchmark proof", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ] ], "meta": [ [ "Base", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "Open-weights / fine-tuning", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (17)", "+0.4" ], [ "Modular src/ architecture", "+0.3" ], [ "Agent / eval harness", "+0.2" ], [ "Automated CI workflow", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Live web deployment", "+0.4" ] ] }, "rank": 250, "is_new": false, "commits_delta": 0, "rank_delta": 9, "commits_delta_last_run": 0 }, { "full_name": "starlord20/bucketwise", "html_url": "https://github.com/starlord20/bucketwise", "track": "Build for Your World", "domain": "Finance, Crypto & Web3", "summary": "Household CFO sorting messy finances into emergency, college, event buckets.", "readme_summary": "Bucketwise ingests Gmail, bank CSVs and 529s into Emergency, College and Life Event buckets. It adds shock-tests for 2008/2020/2022 crises with action-oriented guidance. Next.js app built for family financial planning.", "tech_highlights": [ "Next.js App", "Financial Buckets", "Shock-Test Engine" ], "created_at": "2026-10-26T23:32:56Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 14, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": false, "has_video_demo": true, "video_urls": [ "https://www.loom.com/share/1d965246b5e4492ea5329a3e7e98fe6d" ], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.8, "score_meta_tooling": 1.8, "score_tech_depth": 1.1, "score_demo": 1.5, "score_total": 6.2, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ] ], "tech": [ [ "Base", "+0.3" ], [ "5+ window commits (14)", "+0.2" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Video walkthrough", "+1.1" ] ] }, "rank": 251, "is_new": true, "commits_delta": 14, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "tang-vu/liveworld", "html_url": "https://github.com/tang-vu/liveworld", "track": "Build for Your World", "domain": "Gaming, Entertainment & Creative Media", "summary": "Tabletop studio that turns objects into playable logistics games and tests fixes", "readme_summary": "LiveWorld converts tabletop objects and design intent into a playable logistics game, simulates outcomes, and measures repairs. Includes Kept checkout experiment for visual contrast checks. Uses Muse Spark for rules reasoning and SAM for object segmentation.", "tech_highlights": [ "Muse Spark", "SAM Segmentation", "Node + Simulator" ], "created_at": "2026-10-27T16:12:11Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 11, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": true, "has_tests": true, "has_src": true, "has_ci": true, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.1, "score_meta_tooling": 1.8, "score_tech_depth": 1.3, "score_demo": 1.0, "score_total": 6.2, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "General domain", "+0.2" ], [ "Docker packaging", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ] ], "tech": [ [ "Base", "+0.3" ], [ "5+ window commits (11)", "+0.2" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Automated CI workflow", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 252, "is_new": false, "commits_delta": 0, "rank_delta": -214, "commits_delta_last_run": 0 }, { "full_name": "amiraisse2-a11y/corelog", "html_url": "https://github.com/amiraisse2-a11y/corelog", "track": "Build for Your World", "domain": "Multimodal Vision & Video (SAM / Vision)", "summary": "Turns drill-core tray photos into structured lithology logs for review", "readme_summary": "Converts core-box photos plus optional dictation into draft logs with runs, depths, lithology and fractures. Pipeline uses Muse Spark Open with voting, SAM 3.1 for label recrop, and Muse Voice Transcribe. Python code does quality, arithmetic checks and CSV/JSON export.", "tech_highlights": [ "SAM 3.1 Vision", "Muse Spark Open", "Muse Voice Transcribe" ], "created_at": "2026-10-29T23:50:19Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 11, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": true, "has_tests": true, "has_src": false, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": true, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": true, "live_urls": [ "https://ton-space.hf.space" ], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.2, "score_meta_tooling": 1.8, "score_tech_depth": 0.8, "score_demo": 1.4, "score_total": 6.2, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Docker packaging", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ], [ "Open-weights / fine-tuning", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "5+ window commits (11)", "+0.2" ], [ "Automated test suite", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Live web deployment", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 253, "is_new": true, "commits_delta": 11, "rank_delta": 0, "commits_delta_last_run": 1 }, { "full_name": "light667/Oren-META-AI-HACKATHON", "html_url": "https://github.com/light667/Oren-META-AI-HACKATHON", "track": "Build for Your World", "domain": "Business, Sales & Commerce", "summary": "French-language AI assistant that takes real restaurant orders via link or QR.", "readme_summary": "Oren lets small businesses in Togo launch an assistant from a menu photo and voice note into a verified catalog. Next.js + Supabase app with owner dashboard and customer chat ordering with explicit confirmation. Uses Meta AI for French chat, multimodal catalog extraction and order composition.", "tech_highlights": [ "Next.js + Supabase", "Multimodal Catalog AI", "WhatsApp Ordering" ], "created_at": "2026-10-27T04:27:36Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 10, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": true, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": true, "live_urls": [ "https://oren-six.vercel.app" ], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 1, "score_impact": 2.1, "score_meta_tooling": 1.6, "score_tech_depth": 1.3, "score_demo": 1.2, "score_total": 6.2, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Eval & benchmark proof", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "5+ window commits (10)", "+0.2" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Agent / eval harness", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Live web deployment", "+0.4" ] ] }, "rank": 254, "is_new": false, "commits_delta": 10, "rank_delta": 256, "commits_delta_last_run": 0 }, { "full_name": "nikocallas/unus", "html_url": "https://github.com/nikocallas/unus", "track": "Build for Your World", "domain": "Healthcare, Civic Tech & Sustainability", "summary": "Builds a user-owned health passport from messy PDFs and wearables", "readme_summary": "Ingests lab PDFs, portal exports and wearable data into one structured passport where every fact cites source, page and line. Built with Next.js, Supabase and fixtures/scripts for parsing. Does not diagnose; it transcribes and aligns records with provenance.", "tech_highlights": [ "Next.js + Supabase", "PDF Record Parsing", "Provenance Tracing" ], "created_at": "2026-10-27T19:20:46Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 10, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": true, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": true, "live_urls": [ "https://unus-mu.vercel.app" ], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.6, "score_meta_tooling": 2.3, "score_tech_depth": 1.1, "score_demo": 1.2, "score_total": 6.2, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "High-impact domain", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ], [ "Open-weights / fine-tuning", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "5+ window commits (10)", "+0.2" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Live web deployment", "+0.4" ] ] }, "rank": 255, "is_new": false, "commits_delta": 5, "rank_delta": -26, "commits_delta_last_run": 0 }, { "full_name": "Laingo12/kahie", "html_url": "https://github.com/Laingo12/kahie", "track": "Build for Your World", "domain": "Voice, Speech & Audio AI", "summary": "Malagasy voice notes converted to verified shop ledger and credit history", "readme_summary": "PWA where shopkeepers speak Malagasy/French notes to build a verified sales and debt ledger. Backend transcribes, extracts entries and compiles credit history for microcredit. Built with Python backend, frontend PWA and eval tests.", "tech_highlights": [ "Malagasy Speech-to-Text", "PWA Frontend", "Python Backend + Eval" ], "created_at": "2026-10-27T05:07:42Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 6, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": true, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.1, "score_meta_tooling": 1.8, "score_tech_depth": 1.3, "score_demo": 1.0, "score_total": 6.2, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Eval & benchmark proof", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ] ], "tech": [ [ "Base", "+0.3" ], [ "5+ window commits (6)", "+0.2" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Agent / eval harness", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 256, "is_new": false, "commits_delta": 3, "rank_delta": -131, "commits_delta_last_run": 0 }, { "full_name": "mkinvest57/TWINFORGE", "html_url": "https://github.com/mkinvest57/TWINFORGE", "track": "Push the Frontier", "domain": "Robotics, IoT & Manufacturing", "summary": "Digital twin that predicts ball-to-hoop shots 0.5s ahead and controls via MPC", "readme_summary": "Observes ball and hoop scene, induces physics from observations, predicts trajectory with ghost projection, then sim-to-real MPC control. Uses SAM 3.1 perception by concept plus Muse reasoning via local server.", "tech_highlights": [ "SAM 3.1 Vision", "Sim-to-Real MPC", "Physics Induction" ], "created_at": "2026-10-27T18:21:33Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 3, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": false, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": true, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": true, "live_urls": [ "https://mkinvest57.github.io/TWINFORGE/" ], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.1, "score_meta_tooling": 2.3, "score_tech_depth": 0.6, "score_demo": 1.2, "score_total": 6.2, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "High-impact domain", "+0.4" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ], [ "Open-weights / fine-tuning", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "Automated test suite", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Live web deployment", "+0.4" ] ] }, "rank": 257, "is_new": true, "commits_delta": 3, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "SakkarinKt/eyes-on-qa", "html_url": "https://github.com/SakkarinKt/eyes-on-qa", "track": "Push the Frontier", "domain": "Developer Tooling, Infra & Security", "summary": "Phone-controlled coding team that proves fixes with video verification", "readme_summary": "Multi-agent coding team controlled from phone. Agents record acceptance flows on video, a Meta model judges criteria, SAM 3.1 marks failing elements. Human approves or rejects via LINE before merge.", "tech_highlights": [ "SAM 3.1 Vision", "Muse Video Judge", "LINE + Agents" ], "created_at": "2026-10-26T16:56:13Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 1, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": true, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.3, "score_meta_tooling": 1.8, "score_tech_depth": 1.1, "score_demo": 1.0, "score_total": 6.2, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "High-impact domain", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ] ], "tech": [ [ "Base", "+0.3" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Automated CI workflow", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 258, "is_new": false, "commits_delta": 0, "rank_delta": -82, "commits_delta_last_run": 0 }, { "full_name": "martinmw13/LectorIA-meta", "html_url": "https://github.com/martinmw13/LectorIA-meta", "track": "Build for Your World", "domain": "Education & Knowledge Systems", "summary": "E-reader that scores books with orchestral music and spoiler-free chat", "readme_summary": "Lectoria is an e-reader playing orchestral music matched to each scene emotion of public-domain books. Stack is Next.js with preprocessed scenes, image illustration, read-aloud with word highlight and ducking, plus spoiler-free companion via Meta Muse.", "tech_highlights": [ "Meta Muse models", "Next.js + Vercel", "TTS + adaptive music" ], "created_at": "2026-10-27T18:44:35Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 623, "commits_before_window": 0, "prs_total": 160, "prs_merged": 155, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": true, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": true, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": true, "live_urls": [ "https://lectoria-meta.vercel.app" ], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 1, "score_impact": 1.5, "score_meta_tooling": 1.5, "score_tech_depth": 1.9, "score_demo": 1.2, "score_total": 6.1, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ] ], "meta": [ [ "Base", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ], [ "Open-weights / fine-tuning", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (623)", "+0.6" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Automated CI workflow", "+0.2" ], [ "PR review workflow (155 PRs)", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Live web deployment", "+0.4" ] ] }, "rank": 259, "is_new": false, "commits_delta": 112, "rank_delta": -162, "commits_delta_last_run": 0 }, { "full_name": "OppaAI/Aidon", "html_url": "https://github.com/OppaAI/Aidon", "track": "Push the Frontier", "domain": "Autonomous Agents & Workflow Automation", "summary": "Autonomous agent for safe verifiable goal execution in isolated sandboxes", "readme_summary": "Autonomous AI agent focused on safe, verifiable goal execution. Runs in bubblewrap/Docker sandboxes on Ubuntu with NVIDIA acceleration. Uses Meta models via Modal and Python tooling for constrained execution.", "tech_highlights": [ "Meta Models", "Bubblewrap + Docker", "Modal + Python" ], "created_at": "2026-10-26T17:43:11Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 407, "commits_before_window": 0, "prs_total": 9, "prs_merged": 9, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": true, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 1, "score_impact": 2.3, "score_meta_tooling": 1.3, "score_tech_depth": 1.9, "score_demo": 0.6, "score_total": 6.1, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "High-impact domain", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (407)", "+0.6" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Automated CI workflow", "+0.2" ], [ "PR review workflow (9 PRs)", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 260, "is_new": true, "commits_delta": 407, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "calvinmilliken1994-spec/meta-hackathon-2026", "html_url": "https://github.com/calvinmilliken1994-spec/meta-hackathon-2026", "track": "Build for Your World", "domain": "Education & Knowledge Systems", "summary": "Turns licensed pages into quote-linked lessons with quizzes and simulations", "readme_summary": "Teacher-sourced pages become interactive lessons with quote-linked overviews, quizzes, maps and simulations. Deterministic verifiers check quotes, numbers and formulas with bounded Muse Spark repair. Stack includes JS packages, schemas and scripts for publishing only verified parts.", "tech_highlights": [ "Muse Spark 1.3", "Deterministic Verifier", "Interactive Simulations" ], "created_at": "2026-10-26T17:58:19Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 241, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": true, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.1, "score_meta_tooling": 1.3, "score_tech_depth": 1.7, "score_demo": 1.0, "score_total": 6.1, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Eval & benchmark proof", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (241)", "+0.6" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Agent / eval harness", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 261, "is_new": false, "commits_delta": 240, "rank_delta": 82, "commits_delta_last_run": 9 }, { "full_name": "NotPellew/Thalvi", "html_url": "https://github.com/NotPellew/Thalvi", "track": "Build for Your World", "domain": "Voice, Speech & Audio AI", "summary": "Hands-free self-hosted voice assistant for cooking, driving and messaging", "readme_summary": "Interruptible assistant that sees camera view, plans steps and confirms messages aloud. Uses Muse Voice Transcribe, Muse Spark and SAM 3.1 with local Qwen3-TTS or Kokoro speech.", "tech_highlights": [ "Muse Voice Transcribe", "Muse Spark + SAM 3.1", "Rust Self-Hosted" ], "created_at": "2026-10-26T16:41:27Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 155, "commits_before_window": 0, "prs_total": 35, "prs_merged": 28, "is_preexisting": false, "has_docker": true, "has_tests": false, "has_src": false, "has_ci": true, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.2, "score_meta_tooling": 1.6, "score_tech_depth": 1.3, "score_demo": 1.0, "score_total": 6.1, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Docker packaging", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ], [ "Published HF Hub weights", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (155)", "+0.6" ], [ "Automated CI workflow", "+0.2" ], [ "PR review workflow (28 PRs)", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 262, "is_new": false, "commits_delta": 49, "rank_delta": -164, "commits_delta_last_run": 13 }, { "full_name": "furqaannabi/siteproof", "html_url": "https://github.com/furqaannabi/siteproof", "track": "Build for Your World", "domain": "Multimodal Vision & Video (SAM / Vision)", "summary": "Verifies builder stage payment claims by counting windows and doors in site footage", "readme_summary": "Turns WhatsApp progress clips, demand letters and BOQs into Verified/Short/Not seen verdicts with visual outlines. Stack is web frontend plus backend API with contract parsing and vision counting. Uses Meta Muse models to read documents and reason over detected objects.", "tech_highlights": [ "Vision Detection", "Muse Spark", "Next.js + Backend" ], "created_at": "2026-10-26T16:28:48Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 118, "commits_before_window": 0, "prs_total": 10, "prs_merged": 10, "is_preexisting": false, "has_docker": true, "has_tests": false, "has_src": true, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": true, "live_urls": [ "https://siteproof-alpha.vercel.app" ], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.2, "score_meta_tooling": 1.1, "score_tech_depth": 1.4, "score_demo": 1.4, "score_total": 6.1, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Docker packaging", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (118)", "+0.6" ], [ "Modular src/ architecture", "+0.3" ], [ "PR review workflow (10 PRs)", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Live web deployment", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 263, "is_new": false, "commits_delta": 14, "rank_delta": -134, "commits_delta_last_run": 0 }, { "full_name": "vherediadepvops/ProofLab-AI", "html_url": "https://github.com/vherediadepvops/ProofLab-AI", "track": "Push the Frontier", "domain": "Education & Knowledge Systems", "summary": "Scientific evidence engine testing hypotheses with measurements", "readme_summary": "Competition-edition .NET platform predicts and explains hypothesis-data agreement. Integrates SAM 3.1 for segmentation with mask decoder and Muse Spark for inference and explanations.", "tech_highlights": [ "SAM 3.1 Vision", "Muse Spark", ".NET + Lean" ], "created_at": "2026-10-26T16:48:09Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 111, "commits_before_window": 0, "prs_total": 1, "prs_merged": 1, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": true, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.2, "score_meta_tooling": 1.6, "score_tech_depth": 1.7, "score_demo": 0.6, "score_total": 6.1, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "Domain alignment", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (111)", "+0.6" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Automated CI workflow", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 264, "is_new": false, "commits_delta": 49, "rank_delta": -250, "commits_delta_last_run": 1 }, { "full_name": "flytying/sentralid-trace", "html_url": "https://github.com/flytying/sentralid-trace", "track": "Build for Your World", "domain": "Business, Sales & Commerce", "summary": "Checks Philippine hotel booking links and chats against official records.", "readme_summary": "Trace analyzes Facebook links and chat screenshots with Muse Spark 1.3 via Meta API, compares findings to government-sourced records, and guides users to one safe verification step. Next.js app with eval scripts.", "tech_highlights": [ "Muse Spark 1.3", "Next.js + TypeScript", "Verification Evals" ], "created_at": "2026-10-31T03:57:12Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 62, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": true, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.1, "score_meta_tooling": 1.3, "score_tech_depth": 1.7, "score_demo": 1.0, "score_total": 6.1, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Eval & benchmark proof", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (62)", "+0.6" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Agent / eval harness", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 265, "is_new": true, "commits_delta": 62, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "maxime-mularz/live-cargo-witness", "html_url": "https://github.com/maxime-mularz/live-cargo-witness", "track": "Push the Frontier", "domain": "Autonomous Agents & Workflow Automation", "summary": "Investigator agent audits live-animal air cargo paperwork and flight deviations", "readme_summary": "Black-box agent checks IATA paperwork pre-flight, reconstructs flight post-landing, and queries crew on deviations. Deterministic core with evaluation benches, agent loop, and journal handover record. Runs on Muse Spark Open, SAM 3.1 and Voice Transcribe.", "tech_highlights": [ "Muse Spark Open", "SAM 3.1 Vision", "Voice Transcribe" ], "created_at": "2026-10-26T23:17:43Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 38, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": false, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": true, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.1, "score_meta_tooling": 2.3, "score_tech_depth": 0.7, "score_demo": 1.0, "score_total": 6.1, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "High-impact domain", "+0.4" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ], [ "Open-weights / fine-tuning", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (38)", "+0.4" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 266, "is_new": false, "commits_delta": 0, "rank_delta": -42, "commits_delta_last_run": 0 }, { "full_name": "HarrisHamid/Trace", "html_url": "https://github.com/HarrisHamid/Trace", "track": "Push the Frontier", "domain": "Developer Tooling, Infra & Security", "summary": "Visual graph explorer that lets an agent answer codebase questions.", "readme_summary": "Trace converts a Python repo into an interactive module and function call graph. An AI agent walks the graph to answer questions, with claims checked against the real call graph. Clicking nodes opens exact file lines.", "tech_highlights": [ "Muse Models", "Call-Graph Agent", "Python + Graph UI" ], "created_at": "2026-10-28T04:20:51Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 31, "commits_before_window": 0, "prs_total": 6, "prs_merged": 5, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": true, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.3, "score_meta_tooling": 1.3, "score_tech_depth": 1.7, "score_demo": 0.8, "score_total": 6.1, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "High-impact domain", "+0.4" ], [ "Eval & benchmark proof", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (31)", "+0.4" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Agent / eval harness", "+0.2" ], [ "PR review workflow (5 PRs)", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ] ] }, "rank": 267, "is_new": false, "commits_delta": 29, "rank_delta": 121, "commits_delta_last_run": 0 }, { "full_name": "miravena/worksheet-coach", "html_url": "https://github.com/miravena/worksheet-coach", "track": "Build for Your World", "domain": "Education & Knowledge Systems", "summary": "Photos finished math worksheets to find the core error habit and build targeted practice", "readme_summary": "Photos a completed math worksheet, detects wrong problems and infers the underlying habit. Python agent plus web UI generates a 5-problem practice sheet with self-checked answer key. Built for adult tutors and learners using Muse vision models.", "tech_highlights": [ "Muse Spark Vision", "Python + Web UI", "Math Error Analysis" ], "created_at": "2026-10-26T21:35:13Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 30, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": false, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": true, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.8, "score_meta_tooling": 2.3, "score_tech_depth": 1.0, "score_demo": 1.0, "score_total": 6.1, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ], [ "Open-weights / fine-tuning", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (30)", "+0.4" ], [ "Automated test suite", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 268, "is_new": false, "commits_delta": 21, "rank_delta": 8, "commits_delta_last_run": 0 }, { "full_name": "mkhan48-debug/protocolsmith-meta-hackathon", "html_url": "https://github.com/mkhan48-debug/protocolsmith-meta-hackathon", "track": "Push the Frontier", "domain": "Developer Tooling, Infra & Security", "summary": "Discovers API version differences and builds a verified compatibility bridge", "readme_summary": "Active API-archaeology agent that probes v1 vs v2 APIs to find behavioral breaks and compiles a constrained bridge. Python stack with src/templates/scripts/tests and CI. Uses Muse Spark 1.3 via Meta Model API for analysis and bridge synthesis.", "tech_highlights": [ "Muse Spark 1.3", "Python Agent", "API Migration" ], "created_at": "2026-10-30T00:14:37Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 19, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": true, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 1, "score_impact": 2.3, "score_meta_tooling": 1.3, "score_tech_depth": 1.5, "score_demo": 1.0, "score_total": 6.1, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "High-impact domain", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (19)", "+0.4" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Automated CI workflow", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 269, "is_new": true, "commits_delta": 19, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "KhalidBakroun/nara-application-agent", "html_url": "https://github.com/KhalidBakroun/nara-application-agent", "track": "Build for Your World", "domain": "Education & Knowledge Systems", "summary": "Arabic-first agent turning answers and certificate photos into university application packs", "readme_summary": "Turns student answers and certificate photos into a checkable university application pack for counsellor review. Built with Next.js, Meta models for Arabic extraction and eligibility checks. Live product with class mode and fictional demo data.", "tech_highlights": [ "Muse Spark", "Next.js + Vercel", "Arabic OCR Agent" ], "created_at": "2026-10-30T10:57:45Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 17, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": true, "live_urls": [ "https://nara-application-agent.vercel.app" ], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.8, "score_meta_tooling": 1.6, "score_tech_depth": 1.3, "score_demo": 1.4, "score_total": 6.1, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (17)", "+0.4" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Live web deployment", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 270, "is_new": true, "commits_delta": 17, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "abyaz16/spatialsight", "html_url": "https://github.com/abyaz16/spatialsight", "track": "Push the Frontier", "domain": "Multimodal Vision & Video (SAM / Vision)", "summary": "Compiles fixed-camera video into SQL tables queryable in plain English", "readme_summary": "SpatialSight segments long video with SAM 3.1, resolves stable entities, logs zone entries to SQL, and answers English questions with SQL and frame jumps. Python pipeline with web UI. Uses SAM 3.1 parser and Muse models, with offline fixture mode.", "tech_highlights": [ "SAM 3.1 Vision", "Text-to-SQL", "Python + SQL" ], "created_at": "2026-10-26T19:09:44Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 11, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.2, "score_meta_tooling": 1.8, "score_tech_depth": 1.1, "score_demo": 1.0, "score_total": 6.1, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "Domain alignment", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ] ], "tech": [ [ "Base", "+0.3" ], [ "5+ window commits (11)", "+0.2" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 271, "is_new": true, "commits_delta": 11, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "MichaelGrycz/MetaECU-Copilot", "html_url": "https://github.com/MichaelGrycz/MetaECU-Copilot", "track": "Push the Frontier", "domain": "Robotics, IoT & Manufacturing", "summary": "Verifiable ECU calibration engine with deterministic physics safety gate", "readme_summary": "Reads Bosch EDC16C39 2MiB flash and lets Muse plan calibration from 774-symbol catalogue. Deterministic Safety Gate rejects torque beyond clutch limits and forces replan. Ships patched binary with corrected checksum and audit report.", "tech_highlights": [ "Muse Planning", "Deterministic Safety Gate", "Python + ECU Binary Tools" ], "created_at": "2026-10-29T16:06:24Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 6, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": true, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": true, "live_urls": [ "https://michaelgrycz--metaecu-copilot-web.us-east.modal.run" ], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.3, "score_meta_tooling": 1.6, "score_tech_depth": 0.8, "score_demo": 1.4, "score_total": 6.1, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "High-impact domain", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "5+ window commits (6)", "+0.2" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Live web deployment", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 272, "is_new": true, "commits_delta": 6, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "Diarm10/creative-director-agent-hackathon", "html_url": "https://github.com/Diarm10/creative-director-agent-hackathon", "track": "Build for Your World", "domain": "Business, Sales & Commerce", "summary": "Converts messy product catalogs into reviewed, human-approved ad creatives", "readme_summary": "Creative Director Agent checks photos, segments products, writes headlines, lays out ads and requests approval. Built with a layout engine, review loop, and web demo on Vercel. Uses Meta AI models for vision check and copy generation.", "tech_highlights": [ "Muse Vision + LLM", "Node.js + Vercel", "Human Approval Loop" ], "created_at": "2026-11-01T21:44:06Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 1, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": false, "meta_api_verified": false, "partner_infra": "Baseten", "open_weights_tuning": true, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": true, "live_urls": [ "https://creative-director-agent.vercel.app" ], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.8, "score_meta_tooling": 2.0, "score_tech_depth": 0.9, "score_demo": 1.4, "score_total": 6.1, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ], [ "Partner inference infra", "+0.2" ], [ "Open-weights / fine-tuning", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Live web deployment", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 273, "is_new": true, "commits_delta": 1, "rank_delta": 0, "commits_delta_last_run": 1 }, { "full_name": "PatriaAWijaya/Minime-Hackathon", "html_url": "https://github.com/PatriaAWijaya/Minime-Hackathon", "track": "Push the Frontier", "domain": "Autonomous Agents & Workflow Automation", "summary": "Meta-native multi-agent content orchestrator with human gates and live eval harness", "readme_summary": "Routes a brief across Intake, Research, Strategy and drafting agents with human approval gates. Built in TypeScript/Node with Meta Model API plus Gemini and Ollama routing. Uses Muse models for orchestration and reports routing quality, latency and cost.", "tech_highlights": [ "Muse Models", "Agent Orchestrator", "Eval Harness" ], "created_at": "2026-10-27T01:28:27Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 448, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": true, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": true, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.6, "score_meta_tooling": 1.0, "score_tech_depth": 1.4, "score_demo": 1.0, "score_total": 6.0, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "High-impact domain", "+0.4" ], [ "Eval & benchmark proof", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (448)", "+0.6" ], [ "Modular src/ architecture", "+0.3" ], [ "Agent / eval harness", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 274, "is_new": false, "commits_delta": 269, "rank_delta": -147, "commits_delta_last_run": 0 }, { "full_name": "lleoparden/naqsh", "html_url": "https://github.com/lleoparden/naqsh", "track": "Build for Your World", "domain": "Multimodal Vision & Video (SAM / Vision)", "summary": "Arabic-first localizer turning images into editable translated RTL layers", "readme_summary": "Uploads comics, posters or menus, segments text, translates to Arabic, inpaints originals and re-typesets RTL in matching style. Includes layer editor with SVG/PNG export and replay mode. Uses vision segmentation plus translation models.", "tech_highlights": [ "SAM Vision", "Arabic RTL Typeset", "SVG Layer Editor" ], "created_at": "2026-10-27T12:34:23Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 267, "commits_before_window": 0, "prs_total": 123, "prs_merged": 123, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": true, "has_ci": true, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.8, "score_meta_tooling": 1.6, "score_tech_depth": 1.6, "score_demo": 1.0, "score_total": 6.0, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (267)", "+0.6" ], [ "Modular src/ architecture", "+0.3" ], [ "Automated CI workflow", "+0.2" ], [ "PR review workflow (123 PRs)", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 275, "is_new": false, "commits_delta": 144, "rank_delta": -217, "commits_delta_last_run": 0 }, { "full_name": "imthi16/proofmerge", "html_url": "https://github.com/imthi16/proofmerge", "track": "Push the Frontier", "domain": "Developer Tooling, Infra & Security", "summary": "Blocks bad AI pull requests by running Spark-written tests 3x in sandbox", "readme_summary": "ProofMerge verifies AI coding-agent PRs by having Muse Spark write tests that must pass on base code, running each 3x on base and patch in no-network Docker. Muse Wonder checks Spark's work, plain code decides PASS/REVIEW/BLOCK. Ships as Python CLI and GitHub Action with bench and demo.", "tech_highlights": [ "Muse Spark 1.3", "Muse Wonder 1.0", "Docker Sandbox" ], "created_at": "2026-10-27T06:37:34Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 186, "commits_before_window": 0, "prs_total": 48, "prs_merged": 48, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": true, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.3, "score_meta_tooling": 1.1, "score_tech_depth": 2.0, "score_demo": 0.6, "score_total": 6.0, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "High-impact domain", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (186)", "+0.6" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Agent / eval harness", "+0.2" ], [ "Automated CI workflow", "+0.2" ], [ "PR review workflow (48 PRs)", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 276, "is_new": false, "commits_delta": 112, "rank_delta": -176, "commits_delta_last_run": 0 }, { "full_name": "kryterea/kryterea-lifecycle-copilot", "html_url": "https://github.com/kryterea/kryterea-lifecycle-copilot", "track": "Push the Frontier", "domain": "Developer Tooling, Infra & Security", "summary": "Reviews coding-agent changes with analyst, architect, QA and compliance checks", "readme_summary": "Professional copilot that reviews every coding-agent diff without writing product code. Monorepo with packs, packages and docs pipeline ending in a signable acceptance record. Uses Meta Muse Spark as the reasoning layer for all professional roles.", "tech_highlights": [ "Muse Spark", "Review Agents", "TypeScript Monorepo" ], "created_at": "2026-10-27T00:30:56Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 135, "commits_before_window": 0, "prs_total": 9, "prs_merged": 9, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": true, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.3, "score_meta_tooling": 0.8, "score_tech_depth": 1.9, "score_demo": 1.0, "score_total": 6.0, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "High-impact domain", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Muse Spark integration", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (135)", "+0.6" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Automated CI workflow", "+0.2" ], [ "PR review workflow (9 PRs)", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 277, "is_new": false, "commits_delta": 17, "rank_delta": -218, "commits_delta_last_run": 6 }, { "full_name": "guillemolero10/dockclerk", "html_url": "https://github.com/guillemolero10/dockclerk", "track": "Build for Your World", "domain": "Business, Sales & Commerce", "summary": "AI warehouse clerk that turns emails and photos into ready-to-approve jobs", "readme_summary": "Reads customer emails, WhatsApp and voice notes to prepare work inside existing 3PL software. Counts boxes from delivery-note photos for one-click approval. Next.js plus Prisma and Modal stack built for small Spanish logistics warehouses.", "tech_highlights": [ "Muse Models", "Next.js + Prisma", "Vision Counting" ], "created_at": "2026-10-26T16:29:47Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 128, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": true, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": true, "live_urls": [ "https://dockclerk.vercel.app" ], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.8, "score_meta_tooling": 1.6, "score_tech_depth": 1.2, "score_demo": 1.4, "score_total": 6.0, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (128)", "+0.6" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Live web deployment", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 278, "is_new": false, "commits_delta": 104, "rank_delta": -247, "commits_delta_last_run": 0 }, { "full_name": "Rookweld/FieldRook", "html_url": "https://github.com/Rookweld/FieldRook", "track": "Build for Your World", "domain": "Robotics, IoT & Manufacturing", "summary": "Local-first Windows diagnostic workstation for field technicians", "readme_summary": "Native Windows app collects symptoms and device signals into evidence-backed diagnosis. Local-first architecture with collector, backend, demo worker and safety-focused workflow.", "tech_highlights": [ "Windows Native App", "Local-first Diagnosis", "Evidence Workflow" ], "created_at": "2026-10-27T00:24:11Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 99, "commits_before_window": 0, "prs_total": 3, "prs_merged": 3, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": true, "has_ci": true, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": true, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 1, "score_impact": 2.2, "score_meta_tooling": 1.0, "score_tech_depth": 1.8, "score_demo": 1.0, "score_total": 6.0, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "High-impact domain", "+0.4" ], [ "Eval & benchmark proof", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (99)", "+0.6" ], [ "Modular src/ architecture", "+0.3" ], [ "Agent / eval harness", "+0.2" ], [ "Automated CI workflow", "+0.2" ], [ "PR review workflow (3 PRs)", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 279, "is_new": true, "commits_delta": 99, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "ultraxav/jamesian-layer", "html_url": "https://github.com/ultraxav/jamesian-layer", "track": "Push the Frontier", "domain": "Developer Tooling, Infra & Security", "summary": "Middleware auditing foundation model agency and interoceptive states", "readme_summary": "The Jamesian Layer is agency-auditing middleware that benchmarks foundation models across tasks with logs and reports. Built in Python with pipeline controllers for local, Baseten and Meta runners. Audited 18 models with 111 tests for agent evaluation.", "tech_highlights": [ "Meta Open Weights", "Python Middleware", "Agent Evaluation" ], "created_at": "2026-10-27T03:03:53Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 81, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.3, "score_meta_tooling": 1.6, "score_tech_depth": 1.5, "score_demo": 0.6, "score_total": 6.0, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "High-impact domain", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (81)", "+0.6" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 280, "is_new": false, "commits_delta": 36, "rank_delta": 7, "commits_delta_last_run": 0 }, { "full_name": "Mister-Coolman/wardrobe-stylist", "html_url": "https://github.com/Mister-Coolman/wardrobe-stylist", "track": "Build for Your World", "domain": "General & Emerging Applications", "summary": "Daily outfit from closet video, calendar, weather and laundry state", "readme_summary": "Wardrobe Stylist scans closet via video/photo into tagged garments and builds one daily outfit from calendar and forecast. Next.js, Supabase and packing-list features. Uses Meta AI for garment tagging and outfit reasoning.", "tech_highlights": [ "Next.js + Supabase", "Muse Spark", "Calendar + Weather API" ], "created_at": "2026-10-28T01:23:44Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 78, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.7, "score_meta_tooling": 1.8, "score_tech_depth": 1.5, "score_demo": 1.0, "score_total": 6.0, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "General domain", "+0.2" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (78)", "+0.6" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 281, "is_new": false, "commits_delta": 44, "rank_delta": -177, "commits_delta_last_run": 0 }, { "full_name": "fir3storm/cybergenesis", "html_url": "https://github.com/fir3storm/cybergenesis", "track": "Push the Frontier", "domain": "Developer Tooling, Infra & Security", "summary": "Self-defending digital twin that attacks itself to prove resilience", "readme_summary": "Autonomous cyber defense validation platform that simulates attacks against a digital twin and tests defenses. Moves from alert detection to provable resilience evidence. Powered by Meta Muse Spark with backend and docs architecture.", "tech_highlights": [ "Muse Spark", "Digital Twin Defense", "Adversarial Testing" ], "created_at": "2026-10-26T19:23:52Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 67, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": true, "has_ci": true, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.3, "score_meta_tooling": 1.3, "score_tech_depth": 1.4, "score_demo": 1.0, "score_total": 6.0, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "High-impact domain", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (67)", "+0.6" ], [ "Modular src/ architecture", "+0.3" ], [ "Automated CI workflow", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 282, "is_new": false, "commits_delta": 4, "rank_delta": -124, "commits_delta_last_run": 0 }, { "full_name": "Emmanuel-Onwuka-dev/Quote_Finder", "html_url": "https://github.com/Emmanuel-Onwuka-dev/Quote_Finder", "track": "Build for Your World", "domain": "Gaming, Entertainment & Creative Media", "summary": "Finds a YouTube video from a half-remembered line typed or spoken by the user", "readme_summary": "Matches typed or spoken quote against YouTube titles and descriptions and returns embedded player. Uses YouTube Data API v3, oEmbed, and Meta Muse models, no scraping or downloads. Built with Vite, TypeScript and Vitest.", "tech_highlights": [ "Muse Models", "YouTube Data API v3", "Vite + TypeScript" ], "created_at": "2026-10-28T11:11:08Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 64, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": true, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.4, "score_meta_tooling": 2.3, "score_tech_depth": 1.5, "score_demo": 0.8, "score_total": 6.0, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "General domain", "+0.2" ], [ "Multi-module scope (>10 files)", "+0.2" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ], [ "Open-weights / fine-tuning", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (64)", "+0.6" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ] ] }, "rank": 283, "is_new": false, "commits_delta": 59, "rank_delta": -53, "commits_delta_last_run": 7 }, { "full_name": "xFalzz/verdara", "html_url": "https://github.com/xFalzz/verdara", "track": "Build for Your World", "domain": "Healthcare, Civic Tech & Sustainability", "summary": "3D eco-district twin for spatial climate intelligence and planning", "readme_summary": "Spatial Climate Intelligence platform with autonomous 3D eco-district twin covering 195+ countries. Next.js TypeScript strict frontend with Vitest suite. Uses SAM 3.1 Vision and Muse Spark for spatial analysis.", "tech_highlights": [ "SAM 3.1 Vision", "Muse Spark", "Next.js 3D Twin" ], "created_at": "2026-10-26T15:15:37Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 59, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": true, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 1, "score_impact": 2.2, "score_meta_tooling": 1.1, "score_tech_depth": 1.7, "score_demo": 1.0, "score_total": 6.0, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "High-impact domain", "+0.4" ], [ "Eval & benchmark proof", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (59)", "+0.6" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Agent / eval harness", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 284, "is_new": true, "commits_delta": 59, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "BROCKUGANDA/permitzero", "html_url": "https://github.com/BROCKUGANDA/permitzero", "track": "Push the Frontier", "domain": "Developer Tooling, Infra & Security", "summary": "Zero-trust firewall that authorizes every consequential AI agent action", "readme_summary": "Runtime authorization plane intercepts agent tool calls and binds them to tenant, identity, and argument hash. Allows, denies, or queues for human approval before execution with tamper-evident log. Finance execution simulated for hackathon demo.", "tech_highlights": [ "Zero-Trust Policy", "Approval Gates", "Audit Log" ], "created_at": "2026-10-27T09:56:23Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 37, "commits_before_window": 0, "prs_total": 25, "prs_merged": 14, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": true, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.3, "score_meta_tooling": 1.0, "score_tech_depth": 1.7, "score_demo": 1.0, "score_total": 6.0, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "High-impact domain", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (37)", "+0.4" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Automated CI workflow", "+0.2" ], [ "PR review workflow (14 PRs)", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 285, "is_new": false, "commits_delta": 5, "rank_delta": -219, "commits_delta_last_run": 0 }, { "full_name": "qubitpage/carpathron-muse", "html_url": "https://github.com/qubitpage/carpathron-muse", "track": "Push the Frontier", "domain": "Robotics, IoT & Manufacturing", "summary": "ESP32 camera robot driven by Muse via desktop, WhatsApp, web and Quest 3S", "readme_summary": "Connects ESP32 camera robot to Muse via open robot protocol. Provides Windows agent with PC access, WhatsApp voice/text, browser and Quest 3S avatar control. Includes firmware, protocol, apps and security shield.", "tech_highlights": [ "Muse Spark", "ESP32 + Firmware", "Quest 3S + WhatsApp" ], "created_at": "2026-10-28T14:03:19Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 33, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": false, "has_ci": true, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 1, "score_impact": 2.3, "score_meta_tooling": 1.8, "score_tech_depth": 0.9, "score_demo": 1.0, "score_total": 6.0, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "High-impact domain", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (33)", "+0.4" ], [ "Automated CI workflow", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 286, "is_new": true, "commits_delta": 33, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "techafreshh/argus", "html_url": "https://github.com/techafreshh/argus", "track": "Build for Your World", "domain": "Multimodal Vision & Video (SAM / Vision)", "summary": "Autonomous orbital analyst that plans, verifies and alerts on Earth change", "readme_summary": "Takes regions plus questions and loops plan-acquire-analyze-verify-alert with satellite and climate feeds. Python Docker service with graded reports and human approval. Runs on Muse Spark via Meta Model API.", "tech_highlights": [ "Muse Spark 1.3", "Satellite Vision", "Python + Docker" ], "created_at": "2026-10-28T18:33:19Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 29, "commits_before_window": 0, "prs_total": 25, "prs_merged": 25, "is_preexisting": false, "has_docker": true, "has_tests": true, "has_src": true, "has_ci": true, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.9, "score_meta_tooling": 1.6, "score_tech_depth": 1.7, "score_demo": 0.8, "score_total": 6.0, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Docker packaging", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (29)", "+0.4" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Automated CI workflow", "+0.2" ], [ "PR review workflow (25 PRs)", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ] ] }, "rank": 287, "is_new": true, "commits_delta": 29, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "hsynylmz-umhg/witness", "html_url": "https://github.com/hsynylmz-umhg/witness", "track": "Push the Frontier", "domain": "Robotics, IoT & Manufacturing", "summary": "Verifies fixed-camera assembly logs into evidence-linked findings", "readme_summary": "Reads event logs from assembly procedures to flag coverage gaps, out-of-order steps, and undocumented parts with evidence IDs and hash-chained reports. Deterministic Python pipeline with 147 tests and risk gate docs. Claims offline verification without live model inference.", "tech_highlights": [ "Hash-Chained Reports", "Deterministic Pipeline", "Python Audit Suite" ], "created_at": "2026-10-31T08:13:40Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 27, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": true, "video_urls": [ "https://youtu.be/9k-IgV-YyQs" ], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.0, "score_meta_tooling": 0.8, "score_tech_depth": 1.3, "score_demo": 1.9, "score_total": 6.0, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "High-impact domain", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ] ], "meta": [ [ "Base", "+0.5" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (27)", "+0.4" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Video walkthrough", "+1.1" ], [ "Reproducible setup guide", "+0.4" ] ] }, "rank": 288, "is_new": true, "commits_delta": 27, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "Achraf-ghazouani/sakanfarPlaylab", "html_url": "https://github.com/Achraf-ghazouani/sakanfarPlaylab", "track": "Build for Your World", "domain": "Gaming, Entertainment & Creative Media", "summary": "Turns hand-drawn paper levels and chat prompts into playable browser games", "readme_summary": "Plain HTML/JS + Phaser 3 studio with chat, phone-camera scanning and versioned undo. No-build frontend with /api/agent and /api/scan endpoints. Uses Muse Spark to interpret sketches and generate levels plus a playtest repair agent.", "tech_highlights": [ "Muse Spark", "Phaser 3 + JS", "Vision Scan API" ], "created_at": "2026-10-30T18:27:23Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 25, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": true, "live_urls": [ "https://....vercel.app", "https://sakanfarplaylab.vercel.app" ], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.7, "score_meta_tooling": 1.6, "score_tech_depth": 1.3, "score_demo": 1.4, "score_total": 6.0, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "General domain", "+0.2" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (25)", "+0.4" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Live web deployment", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 289, "is_new": true, "commits_delta": 25, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "hearthacker003366/sentinel-v4", "html_url": "https://github.com/hearthacker003366/sentinel-v4", "track": "Push the Frontier", "domain": "Developer Tooling, Infra & Security", "summary": "AI SOC copilot where red-team bots attack a simulated lab network", "readme_summary": "Dual-system copilot with Laya System-1 triage and Muse Spark System-2 reasoning defending a lab network with human approval. Python orchestrator, model_adapter, redteam bots and dashboard. Uses Laya triage plus Muse Spark reasoning.", "tech_highlights": [ "Muse Spark + Laya", "AI SOC Copilot", "Red-Team Harness" ], "created_at": "2026-10-26T15:14:54Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 24, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": true, "has_eval_benchmarks": false, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 1, "score_impact": 2.3, "score_meta_tooling": 1.8, "score_tech_depth": 1.3, "score_demo": 0.6, "score_total": 6.0, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "High-impact domain", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "Open-weights / fine-tuning", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (24)", "+0.4" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 290, "is_new": false, "commits_delta": 5, "rank_delta": -167, "commits_delta_last_run": 0 }, { "full_name": "silambarasan-sh/kadai-khata", "html_url": "https://github.com/silambarasan-sh/kadai-khata", "track": "Build for Your World", "domain": "Business, Sales & Commerce", "summary": "Tanglish text, voice and photo ledger for kirana shop credit tracking", "readme_summary": "Digitizes Tamil Nadu kirana udhaar notebooks via Tanglish text, voice, and notebook photos to reduce disputes and loss. Built with Django, handles Tamil numerals and shorthand, deployed on Render with live demo.", "tech_highlights": [ "Tanglish NLP", "Voice + OCR Ledger", "Django on Render" ], "created_at": "2026-10-27T04:38:59Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 22, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": false, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": true, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": true, "live_urls": [ "https://kadai-khata.onrender.com" ], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.8, "score_meta_tooling": 1.8, "score_tech_depth": 1.0, "score_demo": 1.4, "score_total": 6.0, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "Open-weights / fine-tuning", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (22)", "+0.4" ], [ "Automated test suite", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Live web deployment", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 291, "is_new": false, "commits_delta": 9, "rank_delta": -120, "commits_delta_last_run": 0 }, { "full_name": "Mariavmyers/linguacheck", "html_url": "https://github.com/Mariavmyers/linguacheck", "track": "Push the Frontier", "domain": "Legal & Compliance", "summary": "Evaluator checking if Meta models give same medical-legal facts across languages", "readme_summary": "Cross-lingual factual consistency evaluator asking same medical/legal questions in English and Brazilian Portuguese. Compares answers to flag drift in facts, warnings and deadlines via Gradio app.", "tech_highlights": [ "Meta AI Audit", "Gradio + Python", "Drift Detection" ], "created_at": "2026-10-27T16:57:47Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 22, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": false, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": true, "has_eval_benchmarks": true, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.2, "score_meta_tooling": 1.8, "score_tech_depth": 1.2, "score_demo": 0.8, "score_total": 6.0, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "Domain alignment", "+0.3" ], [ "Eval & benchmark proof", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "Open-weights / fine-tuning", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (22)", "+0.4" ], [ "Automated test suite", "+0.3" ], [ "Agent / eval harness", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ] ] }, "rank": 292, "is_new": false, "commits_delta": 18, "rank_delta": 93, "commits_delta_last_run": 0 }, { "full_name": "averagebonsai/hypothesis", "html_url": "https://github.com/averagebonsai/hypothesis", "track": "Push the Frontier", "domain": "Developer Tooling, Infra & Security", "summary": "Composable Python toolkit to simulate LLM policies against game-theory benchmarks", "readme_summary": "Provides abstract Policy, protocol, and benchmark interfaces for scripted and LLM-driven microeconomic simulations like Bertrand and Stackelberg. Built with Python, pytest, ruff, mypy and Jupyter visualisations with deterministic fake gateways. Uses generic LLM policies for payoff-matrix play with provenance and offline verification.", "tech_highlights": [ "LLM Policy Simulation", "Game-Theory Benchmarks", "Python + Jupyter" ], "created_at": "2026-10-28T04:06:07Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 10, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": true, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.4, "score_meta_tooling": 1.3, "score_tech_depth": 1.3, "score_demo": 1.0, "score_total": 6.0, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "High-impact domain", "+0.4" ], [ "Eval & benchmark proof", "+0.3" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "5+ window commits (10)", "+0.2" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Agent / eval harness", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 293, "is_new": false, "commits_delta": 7, "rank_delta": 169, "commits_delta_last_run": 0 }, { "full_name": "Darsh1222/tmrw-lens", "html_url": "https://github.com/Darsh1222/tmrw-lens", "track": "Build for Your World", "domain": "Education & Knowledge Systems", "summary": "Photographs schedules and whiteboards to build a verified plan that rebuilds when you slip", "readme_summary": "Tomorrow Lens extracts items from screenshots, PDFs and photos, verifies with quotes and date checks, then schedules via rebuild agent. Next.js app with CLAUDE.md, evals and fixtures. Uses Muse Spark for extraction and SAM 3.1 for vision.", "tech_highlights": [ "Muse Spark", "SAM 3.1 Vision", "Next.js + Rebuild Agent" ], "created_at": "2026-10-28T16:26:53Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 6, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": true, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": true, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.1, "score_meta_tooling": 1.6, "score_tech_depth": 1.5, "score_demo": 0.8, "score_total": 6.0, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Eval & benchmark proof", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "5+ window commits (6)", "+0.2" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Agent / eval harness", "+0.2" ], [ "Automated CI workflow", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ] ] }, "rank": 294, "is_new": false, "commits_delta": 5, "rank_delta": 122, "commits_delta_last_run": 1 }, { "full_name": "Anxy/rouvr", "html_url": "https://github.com/Anxy/rouvr", "track": "Push the Frontier", "domain": "Autonomous Agents & Workflow Automation", "summary": "Autonomous colleague turning messy instructions into verified work with receipts", "readme_summary": "Python 3.12 agent framework that converts instructions into agreed contracts, executes with authority limits, then independently verifies. Model-agnostic, powered by Hyeve.", "tech_highlights": [ "Autonomous Agents", "Contract + Verification", "Python 3.12 CLI" ], "created_at": "2026-10-27T16:03:00Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 4, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": true, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": true, "live_urls": [ "https://rouvr.ai" ], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.3, "score_meta_tooling": 1.0, "score_tech_depth": 1.3, "score_demo": 1.4, "score_total": 6.0, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "High-impact domain", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Agent / eval harness", "+0.2" ], [ "Automated CI workflow", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Live web deployment", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 295, "is_new": true, "commits_delta": 4, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "carlosfcosme/trust-proof-work", "html_url": "https://github.com/carlosfcosme/trust-proof-work", "track": "Push the Frontier", "domain": "Developer Tooling, Infra & Security", "summary": "Public trust record scoring AI agents on identity, delivery, and refusals", "readme_summary": "Verifies agent skills via corpus gate, gauntlet benchmarks, and escrow invariants I1-I6. Python rig with locked fixtures and demo scorecard proves install safety and burn detection.", "tech_highlights": [ "Agent Eval Gauntlet", "Escrow Invariants", "Python Gate + Demo" ], "created_at": "2026-10-30T16:06:19Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 2, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": false, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": true, "has_setup_guide": false, "has_video_demo": true, "video_urls": [ "https://www.youtube.com/watch?v=LXloegum4Rc" ], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.4, "score_meta_tooling": 1.3, "score_tech_depth": 0.8, "score_demo": 1.5, "score_total": 6.0, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "High-impact domain", "+0.4" ], [ "Eval & benchmark proof", "+0.3" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "Automated test suite", "+0.3" ], [ "Agent / eval harness", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Video walkthrough", "+1.1" ] ] }, "rank": 296, "is_new": true, "commits_delta": 2, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "gunbaz/gozum", "html_url": "https://github.com/gunbaz/gozum", "track": "Build for Your World", "domain": "Healthcare, Civic Tech & Sustainability", "summary": "Turkish voice wayfinding aid that guides blind users to objects via camera", "readme_summary": "Turkish find-and-guide agent for blind users. Runs a multi-step loop over camera frames where Muse Spark plans JSON actions like locate and read_text. Server executes guidance with clock-face directions and full-resolution text reading.", "tech_highlights": [ "Muse Spark", "Clock-face Guidance", "Turkish Voice UI" ], "created_at": "2026-10-28T20:42:44Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 1, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": true, "has_tests": true, "has_src": true, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": true, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.3, "score_meta_tooling": 1.8, "score_tech_depth": 1.1, "score_demo": 0.8, "score_total": 6.0, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "High-impact domain", "+0.4" ], [ "Eval & benchmark proof", "+0.3" ], [ "Docker packaging", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ] ], "tech": [ [ "Base", "+0.3" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Agent / eval harness", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ] ] }, "rank": 297, "is_new": false, "commits_delta": 0, "rank_delta": -133, "commits_delta_last_run": 0 }, { "full_name": "vibhortayal/arya", "html_url": "https://github.com/vibhortayal/arya", "track": "Build for Your World", "domain": "Business, Sales & Commerce", "summary": "Grocery list that learns habits from receipts and maps store routes", "readme_summary": "Arya reads receipts, verifies totals, learns purchase frequency and drafts replenishment lists. Provides a store-model quest UI, Lists API, and live demo sandbox. Built with Meta Muse models for the hackathon.", "tech_highlights": [ "Muse Models", "Receipt OCR", "Lists API" ], "created_at": "2026-10-27T19:13:55Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 1189, "commits_before_window": 0, "prs_total": 368, "prs_merged": 344, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": false, "has_ci": true, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": true, "has_eval_benchmarks": false, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": true, "live_urls": [ "https://arya.teamnightshift.org/" ], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 1, "score_impact": 1.8, "score_meta_tooling": 1.8, "score_tech_depth": 1.3, "score_demo": 1.0, "score_total": 5.9, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ], [ "Open-weights / fine-tuning", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (1189)", "+0.6" ], [ "Automated CI workflow", "+0.2" ], [ "PR review workflow (344 PRs)", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Live web deployment", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 298, "is_new": true, "commits_delta": 1189, "rank_delta": 0, "commits_delta_last_run": 2 }, { "full_name": "Ewrdad/Kainbain", "html_url": "https://github.com/Ewrdad/Kainbain", "track": "Push the Frontier", "domain": "Developer Tooling, Infra & Security", "summary": "Multi-stage AI task orchestrator with kanban review and re-routing", "readme_summary": "KainBain defines workflow pipelines and executes stages via AI agents for human review. Fastify backend with domain stores, WebSocket updates and disk-persisted sessions. React Vite frontend plus Playwright canary tests.", "tech_highlights": [ "Fastify + WebSocket", "React Vite Kanban", "PI Agent SDK" ], "created_at": "2026-10-26T08:14:15Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 557, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": true, "has_tests": true, "has_src": true, "has_ci": true, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.7, "score_meta_tooling": 0.5, "score_tech_depth": 1.7, "score_demo": 1.0, "score_total": 5.9, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "High-impact domain", "+0.4" ], [ "Docker packaging", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (557)", "+0.6" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Automated CI workflow", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 299, "is_new": true, "commits_delta": 557, "rank_delta": 0, "commits_delta_last_run": 9 }, { "full_name": "mkhsu2002/MuseCondo", "html_url": "https://github.com/mkhsu2002/MuseCondo", "track": "Push the Frontier", "domain": "Autonomous Agents & Workflow Automation", "summary": "Open framework for agents to build and keep persistent digital homes", "readme_summary": "MuseCondo explores verifiable, persistent agent identity via Neo Babylon City and Muse Tower. Agents can build, personalize, deploy and maintain homes. It is agent-native open source under Apache 2.0.", "tech_highlights": [ "Muse Agent Tower", "Agent Identity MVP", "Open-Source Framework" ], "created_at": "2026-10-28T07:08:42Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 358, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": true, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": true, "live_urls": [ "https://musecondo.neobabylon.app/" ], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 1, "score_impact": 2.3, "score_meta_tooling": 0.5, "score_tech_depth": 1.7, "score_demo": 1.4, "score_total": 5.9, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "High-impact domain", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (358)", "+0.6" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Automated CI workflow", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Live web deployment", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 300, "is_new": true, "commits_delta": 358, "rank_delta": 0, "commits_delta_last_run": 20 }, { "full_name": "ExtraBinoss/MusArt", "html_url": "https://github.com/ExtraBinoss/MusArt", "track": "Build for Your World", "domain": "Gaming, Entertainment & Creative Media", "summary": "Browser studio for layered posters, graphics and visual experiments", "readme_summary": "Melt combines images, typography, shapes and effects in editable compositions with export and timelapse. Projects save locally with no account, free and open source. Web app with docs and headless mode built for Meta hackathon.", "tech_highlights": [ "Web Editor", "Local-first Storage", "Headless Mode" ], "created_at": "2026-10-28T08:12:08Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 266, "commits_before_window": 0, "prs_total": 2, "prs_merged": 2, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": true, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": true, "has_eval_benchmarks": false, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": true, "live_urls": [ "https://extrabinoss.github.io/MusArt/" ], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.7, "score_meta_tooling": 1.5, "score_tech_depth": 1.7, "score_demo": 1.0, "score_total": 5.9, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "General domain", "+0.2" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Open-weights / fine-tuning", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (266)", "+0.6" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Automated CI workflow", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Live web deployment", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 301, "is_new": true, "commits_delta": 266, "rank_delta": 0, "commits_delta_last_run": 7 }, { "full_name": "uwazzi/hoolala", "html_url": "https://github.com/uwazzi/hoolala", "track": "Build for Your World", "domain": "General & Emerging Applications", "summary": "Anonymous local invitations that turn shared places into real meetups", "readme_summary": "People at same cafe or coworking post anonymous invitations, stay hidden until mutual yes, then meet in person. Muse Spark profiles with consent, suggests topics, screens and translates posts, and proposes venues. Measures accepted invites to conversations.", "tech_highlights": [ "Muse Spark 1.3", "Cloudflare Workers", "Mutual-Opt-In Match" ], "created_at": "2026-10-26T16:37:59Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 155, "commits_before_window": 0, "prs_total": 32, "prs_merged": 32, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": true, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": true, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.0, "score_meta_tooling": 1.3, "score_tech_depth": 2.0, "score_demo": 0.6, "score_total": 5.9, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "General domain", "+0.2" ], [ "Eval & benchmark proof", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (155)", "+0.6" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Agent / eval harness", "+0.2" ], [ "Automated CI workflow", "+0.2" ], [ "PR review workflow (32 PRs)", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 302, "is_new": false, "commits_delta": 101, "rank_delta": -238, "commits_delta_last_run": 0 }, { "full_name": "masontmorris/unity-playtest-agent", "html_url": "https://github.com/masontmorris/unity-playtest-agent", "track": "Push the Frontier", "domain": "Developer Tooling, Infra & Security", "summary": "Autonomous agent that plays Unity games and files evidence-backed bug reports.", "readme_summary": "Point it at a Unity project with objective and budget; it learns controls from code, plays in real time and reproduces bugs. Python harness with Unity bridge and benchmark suite. Uses fast decision model with escalation to stronger Muse Spark model.", "tech_highlights": [ "Muse Spark 1.3", "Unity Bridge + Python", "Auto Bug Reports" ], "created_at": "2026-10-26T16:29:46Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 141, "commits_before_window": 0, "prs_total": 101, "prs_merged": 100, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": true, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": true, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 1, "score_impact": 2.3, "score_meta_tooling": 0.8, "score_tech_depth": 2.0, "score_demo": 0.8, "score_total": 5.9, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "High-impact domain", "+0.4" ], [ "Eval & benchmark proof", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ] ], "meta": [ [ "Base", "+0.5" ], [ "Muse Spark integration", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (141)", "+0.6" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Agent / eval harness", "+0.2" ], [ "Automated CI workflow", "+0.2" ], [ "PR review workflow (100 PRs)", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ] ] }, "rank": 303, "is_new": false, "commits_delta": 63, "rank_delta": -95, "commits_delta_last_run": 0 }, { "full_name": "vbabenko97/fullaura", "html_url": "https://github.com/vbabenko97/fullaura", "track": "Build for Your World", "domain": "Business, Sales & Commerce", "summary": "Builds style plans from wardrobe, budget and real shoppable products with try-on previews.", "readme_summary": "FullAura collects style goals, sizes and budget to generate three constraint-checked looks from real Austria-shipping catalog. Users can keep items, swap, lower budget, and preview on own photos experimentally. Closed beta on Azure with Python backend, frontend, and infra.", "tech_highlights": [ "Meta AI Backend", "Python + Frontend", "Azure Container App" ], "created_at": "2026-10-26T19:34:09Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 127, "commits_before_window": 0, "prs_total": 64, "prs_merged": 64, "is_preexisting": false, "has_docker": true, "has_tests": true, "has_src": true, "has_ci": true, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.2, "score_meta_tooling": 0.8, "score_tech_depth": 1.9, "score_demo": 1.0, "score_total": 5.9, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Docker packaging", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Muse Spark integration", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (127)", "+0.6" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Automated CI workflow", "+0.2" ], [ "PR review workflow (64 PRs)", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 304, "is_new": false, "commits_delta": 86, "rank_delta": -122, "commits_delta_last_run": 4 }, { "full_name": "srcacahuate619/moldesign-molchat", "html_url": "https://github.com/srcacahuate619/moldesign-molchat", "track": "Push the Frontier", "domain": "Autonomous Agents & Workflow Automation", "summary": "Auditable lab agent running computational chemistry via chat/voice", "readme_summary": "Sidecar agent for MolDesign platform proposes verifiable plans and executes jobs via versioned HTTP API. Supports text/voice, human approval gates, hypothesis cycles and provenance acts.", "tech_highlights": [ "Lab Agent + HITL", "Voice to Workflow", "HTTP Sidecar API" ], "created_at": "2026-10-27T04:54:33Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 127, "commits_before_window": 0, "prs_total": 1, "prs_merged": 1, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": true, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.3, "score_meta_tooling": 1.3, "score_tech_depth": 1.7, "score_demo": 0.6, "score_total": 5.9, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "High-impact domain", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (127)", "+0.6" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Automated CI workflow", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 305, "is_new": true, "commits_delta": 127, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "eeshsingh123/Rewind", "html_url": "https://github.com/eeshsingh123/Rewind", "track": "Build for Your World", "domain": "Multimodal Vision & Video (SAM / Vision)", "summary": "Asks any photo or video questions by chat or voice with video clip proof", "readme_summary": "Web, Telegram and WhatsApp bot that answers plain-language questions over user footage. Plans with Muse Spark, tracks with SAM 3.1, transcribes with Muse Voice, verifies with code. Python service with ffmpeg, evals and sim harness.", "tech_highlights": [ "SAM 3.1 Vision", "Muse Spark", "Muse Voice" ], "created_at": "2026-10-27T20:55:47Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 115, "commits_before_window": 0, "prs_total": 19, "prs_merged": 19, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": true, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": true, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.8, "score_meta_tooling": 1.3, "score_tech_depth": 2.0, "score_demo": 0.8, "score_total": 5.9, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Eval & benchmark proof", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ] ], "meta": [ [ "Base", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (115)", "+0.6" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Agent / eval harness", "+0.2" ], [ "Automated CI workflow", "+0.2" ], [ "PR review workflow (19 PRs)", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ] ] }, "rank": 306, "is_new": false, "commits_delta": 37, "rank_delta": -51, "commits_delta_last_run": 0 }, { "full_name": "SergoVashakmadze/iomarkets-live-studio", "html_url": "https://github.com/SergoVashakmadze/iomarkets-live-studio", "track": "Build for Your World", "domain": "Gaming, Entertainment & Creative Media", "summary": "Live AI news studio with virtual anchor, fact-checking and background removal", "readme_summary": "Live interview studio where an AI anchor talks to guests in real time for business news. Listens, fact-checks and segments background for broadcast-ready output. Uses Meta models via META_API_KEY with Python studio CLI architecture.", "tech_highlights": [ "Meta Models", "Live AV Pipeline", "Python + uv" ], "created_at": "2026-10-26T13:32:10Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 106, "commits_before_window": 0, "prs_total": 40, "prs_merged": 39, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": true, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": true, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.4, "score_meta_tooling": 1.8, "score_tech_depth": 1.9, "score_demo": 0.8, "score_total": 5.9, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "General domain", "+0.2" ], [ "Multi-module scope (>10 files)", "+0.2" ] ], "meta": [ [ "Base", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ], [ "Open-weights / fine-tuning", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (106)", "+0.6" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Automated CI workflow", "+0.2" ], [ "PR review workflow (39 PRs)", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ] ] }, "rank": 307, "is_new": false, "commits_delta": 61, "rank_delta": -116, "commits_delta_last_run": 0 }, { "full_name": "EdwinSteve/FieldPilot", "html_url": "https://github.com/EdwinSteve/FieldPilot", "track": "Build for Your World", "domain": "Healthcare, Civic Tech & Sustainability", "summary": "Crop-cycle agent that reads sensors and satellite to plan farm tasks safely", "readme_summary": "Runs a crop cycle from soil sensors, satellite imagery, forecasts and crop catalog. Agent uses autonomy gate for autonomous, notify, or approval actions with event log and Spanish reports. Built as Indie Build for Your World with voice/text frontend.", "tech_highlights": [ "Agentic Crop Cycle", "Satellite + Sensors", "Autonomy Gate" ], "created_at": "2026-10-27T04:50:21Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 76, "commits_before_window": 0, "prs_total": 18, "prs_merged": 18, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": true, "has_ci": true, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.7, "score_meta_tooling": 1.6, "score_tech_depth": 1.6, "score_demo": 1.0, "score_total": 5.9, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "High-impact domain", "+0.4" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (76)", "+0.6" ], [ "Modular src/ architecture", "+0.3" ], [ "Automated CI workflow", "+0.2" ], [ "PR review workflow (18 PRs)", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 308, "is_new": true, "commits_delta": 76, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "bAIwor/bakpao-agent", "html_url": "https://github.com/bAIwor/bakpao-agent", "track": "Build for Your World", "domain": "Business, Sales & Commerce", "summary": "Autonomous micro-bakery ops agent for QRIS, sizing, and food costs", "readme_summary": "Autonomous commerce agent for Banyumas warung managing QRIS payments, HPP, and kitchen ops. Modal CPU + Python stack runs SAM 2.1 for physical measurement. Uses Meta open-weights and Meta AI tooling for vision and ops.", "tech_highlights": [ "SAM 2.1 Vision", "Modal CPU", "QRIS Verification" ], "created_at": "2026-10-28T22:01:21Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 62, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.8, "score_meta_tooling": 1.6, "score_tech_depth": 1.5, "score_demo": 1.0, "score_total": 5.9, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (62)", "+0.6" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 309, "is_new": false, "commits_delta": 9, "rank_delta": -260, "commits_delta_last_run": 0 }, { "full_name": "Qwirlex/twin-closet", "html_url": "https://github.com/Qwirlex/twin-closet", "track": "Build for Your World", "domain": "Business, Sales & Commerce", "summary": "Virtual try-on that shows new clothes on your body styled with your closet", "readme_summary": "Twin Closet scans body and closet, then shows store screenshots on user from four angles and builds outfits. Web + API + Supabase stack with Vercel/Render demo. Built on SAM 3.1, Muse Spark, Muse Image and Muse Voice Transcribe.", "tech_highlights": [ "SAM 3.1 Vision", "Muse Spark", "Muse Image" ], "created_at": "2026-10-25T16:08:55Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 48, "commits_before_window": 8, "prs_total": 0, "prs_merged": 0, "is_preexisting": true, "has_docker": true, "has_tests": false, "has_src": true, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": true, "live_urls": [ "https://twin-closet.vercel.app", "https://twin-closet-api.onrender.com/health" ], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.2, "score_meta_tooling": 1.3, "score_tech_depth": 1.0, "score_demo": 1.4, "score_total": 5.9, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Docker packaging", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (48)", "+0.4" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Live web deployment", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 310, "is_new": false, "commits_delta": 9, "rank_delta": -245, "commits_delta_last_run": 0 }, { "full_name": "peteroraz/naijaledger", "html_url": "https://github.com/peteroraz/naijaledger", "track": "Build for Your World", "domain": "Finance, Crypto & Web3", "summary": "Reconciliation copilot turns daybooks, invoices and voice into settled books", "readme_summary": "NaijaLedger ingests handwritten books, PDFs, voice and CSVs for deterministic match suggestions and tax readiness. Firebase + Cloud Run web app uses Meta models for Smart Intake extraction with human-approved allocations.", "tech_highlights": [ "Meta Models", "Firebase + Cloud Run", "OCR + Voice Intake" ], "created_at": "2026-10-27T22:42:04Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 43, "commits_before_window": 0, "prs_total": 4, "prs_merged": 4, "is_preexisting": false, "has_docker": true, "has_tests": false, "has_src": true, "has_ci": true, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.2, "score_meta_tooling": 1.3, "score_tech_depth": 1.4, "score_demo": 1.0, "score_total": 5.9, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Docker packaging", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (43)", "+0.4" ], [ "Modular src/ architecture", "+0.3" ], [ "Automated CI workflow", "+0.2" ], [ "PR review workflow (4 PRs)", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 311, "is_new": false, "commits_delta": 18, "rank_delta": -205, "commits_delta_last_run": 0 }, { "full_name": "KryomLabs/kryomcode", "html_url": "https://github.com/KryomLabs/kryomcode", "track": "Push the Frontier", "domain": "Developer Tooling, Infra & Security", "summary": "Review-first Electron coding workspace with Meta AI chat, agent and research panel", "readme_summary": "Open-source desktop IDE with Monaco editor, terminal, Git tools and Meta AI chat/agent requiring explicit approval for edits. Electron app with Research-Plan-Review-Execute-Verify workflow and backend limitations documented.", "tech_highlights": [ "Electron + Monaco", "Meta AI Agent", "Muse Models" ], "created_at": "2026-10-26T19:43:08Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 40, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": true, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 2, "score_impact": 2.3, "score_meta_tooling": 1.1, "score_tech_depth": 1.5, "score_demo": 1.0, "score_total": 5.9, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "High-impact domain", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (40)", "+0.4" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Automated CI workflow", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 312, "is_new": true, "commits_delta": 40, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "butchewing/itemized", "html_url": "https://github.com/butchewing/itemized", "track": "Build for Your World", "domain": "Legal & Compliance", "summary": "Checks funeral price lists against FTC Funeral Rule disclosures", "readme_summary": "Uploads funeral home GPLs as PDF or photos and flags missing prices and disclosures with citations. Built for the hackathon and live at itemized.mortuary.ai on Cloudflare Workers. Uses Muse models for document parsing and rule checking.", "tech_highlights": [ "Muse Spark", "Cloudflare Workers", "FTC Rule Checks" ], "created_at": "2026-10-26T16:42:18Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 36, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": false, "meta_api_verified": true, "partner_infra": "Baseten", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": true, "live_urls": [ "https://itemized.mortuary.ai", "https://deploy.workers.cloudflare.com/button", "https://deploy.workers.cloudflare.com/?url=https://github.com/butchewing/itemized" ], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.8, "score_meta_tooling": 1.8, "score_tech_depth": 1.3, "score_demo": 1.0, "score_total": 5.9, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "Partner inference infra", "+0.2" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (36)", "+0.4" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Live web deployment", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 313, "is_new": false, "commits_delta": 0, "rank_delta": -272, "commits_delta_last_run": 0 }, { "full_name": "hackers-dot/maya-hackathon", "html_url": "https://github.com/hackers-dot/maya-hackathon", "track": "Push the Frontier", "domain": "Developer Tooling, Infra & Security", "summary": "Security agent that scans owned sites and proves fixes with evidence.", "readme_summary": "AI security agent that verifies target ownership then runs safe non-destructive checks. Produces evidence-backed reports with severity, plain-language explanation and human-approved patches. Built in Python with httpx and pydantic, plus pytest evals.", "tech_highlights": [ "Python Security Agent", "Evidence Reports", "Pytest Evals" ], "created_at": "2026-10-27T06:17:10Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 31, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": true, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.6, "score_meta_tooling": 0.8, "score_tech_depth": 1.5, "score_demo": 1.0, "score_total": 5.9, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "High-impact domain", "+0.4" ], [ "Eval & benchmark proof", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Muse Spark integration", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (31)", "+0.4" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Agent / eval harness", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 314, "is_new": false, "commits_delta": 0, "rank_delta": -209, "commits_delta_last_run": 0 }, { "full_name": "Giochvanno/hackathon-meta-galileo", "html_url": "https://github.com/Giochvanno/hackathon-meta-galileo", "track": "Build for Your World", "domain": "Education & Knowledge Systems", "summary": "Turns phone videos of pendulums into physics measurements with g estimates", "readme_summary": "Galileo tracks motion frame-by-frame with SAM 3.1, fits competing physical models with uncertainties, and uses Muse Spark agent to select models and verify predictions. Python package with CI and tests.", "tech_highlights": [ "SAM 3.1 Tracking", "Muse Spark Agent", "Python + Physics Fit" ], "created_at": "2026-10-30T07:24:12Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 29, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": true, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 1, "score_impact": 1.6, "score_meta_tooling": 1.8, "score_tech_depth": 1.5, "score_demo": 1.0, "score_total": 5.9, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (29)", "+0.4" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Automated CI workflow", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 315, "is_new": true, "commits_delta": 29, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "musclehed03/hive-mind-mcp", "html_url": "https://github.com/musclehed03/hive-mind-mcp", "track": "Build for Your World", "domain": "Developer Tooling, Infra & Security", "summary": "Shared persistent-memory MCP server with compressed recall payloads", "readme_summary": "MCP server providing one shared memory layer for clients and sub-bots with provenance verification and 3-tier temporal index. Includes Docker setup, GUI, and 247-test suite per README.", "tech_highlights": [ "MCP Server", "Persistent Memory", "Docker + Python" ], "created_at": "2026-10-28T01:35:40Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 25, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": true, "has_tests": true, "has_src": true, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.3, "score_meta_tooling": 1.3, "score_tech_depth": 1.3, "score_demo": 1.0, "score_total": 5.9, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "High-impact domain", "+0.4" ], [ "Docker packaging", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (25)", "+0.4" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 316, "is_new": false, "commits_delta": 22, "rank_delta": 145, "commits_delta_last_run": 0 }, { "full_name": "Swayam13-exe/VoltProof", "html_url": "https://github.com/Swayam13-exe/VoltProof", "track": "Build for Your World", "domain": "Healthcare, Civic Tech & Sustainability", "summary": "Plans solar-battery dispatch from plain-language goals with verification", "readme_summary": "VoltProof is an early-stage AI operator for rooftop solar plus battery on time-of-day tariffs. Currently implements Muse Spark Open client with disk cache, spend ledger and retries. Optimizer, verifier, agent and web UI are not yet built.", "tech_highlights": [ "Muse Spark Open", "Python optimizer", "Budget guard + cache" ], "created_at": "2026-10-27T19:10:49Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 20, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": true, "has_tests": true, "has_src": true, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": true, "has_eval_benchmarks": true, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 1, "score_impact": 2.3, "score_meta_tooling": 1.3, "score_tech_depth": 1.5, "score_demo": 0.8, "score_total": 5.9, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "High-impact domain", "+0.4" ], [ "Eval & benchmark proof", "+0.3" ], [ "Docker packaging", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ] ], "meta": [ [ "Base", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "Open-weights / fine-tuning", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (20)", "+0.4" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Agent / eval harness", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ] ] }, "rank": 317, "is_new": false, "commits_delta": 15, "rank_delta": 33, "commits_delta_last_run": 0 }, { "full_name": "krishsah01/blackbox", "html_url": "https://github.com/krishsah01/blackbox", "track": "Push the Frontier", "domain": "Developer Tooling, Infra & Security", "summary": "Local project memory that answers why-chains and as-of questions with citations.", "readme_summary": "Blackbox stores decisions, commits, document versions, recordings and agent sessions in SQLite. Node TypeScript CLI answers why and as-of queries with supported labels. Uses retrieval over local project history rather than live model claims.", "tech_highlights": [ "Node.js + SQLite", "Retrieval + Citations", "TypeScript CLI" ], "created_at": "2026-10-27T06:50:27Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 18, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": true, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.3, "score_meta_tooling": 1.5, "score_tech_depth": 1.3, "score_demo": 0.8, "score_total": 5.9, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "High-impact domain", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ], [ "Open-weights / fine-tuning", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (18)", "+0.4" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ] ] }, "rank": 318, "is_new": false, "commits_delta": 0, "rank_delta": -101, "commits_delta_last_run": 0 }, { "full_name": "Vaibhav-CD/SmartInk", "html_url": "https://github.com/Vaibhav-CD/SmartInk", "track": "Build for Your World", "domain": "Education & Knowledge Systems", "summary": "Infinite canvas notebook with inking, live math, PDF studio and AI research copilot.", "readme_summary": "Spatial infinite-canvas notebook with pen smoothing, zoom and minimap, living calculations, and multilingual PDF reading with voice. Built with React Vite Tailwind and powered by Meta multimodal models for research assistance.", "tech_highlights": [ "Meta Multimodal AI", "React + Vite", "Infinite Canvas" ], "created_at": "2026-10-29T07:36:44Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 12, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": true, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": true, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.8, "score_meta_tooling": 2.3, "score_tech_depth": 0.8, "score_demo": 1.0, "score_total": 5.9, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ], [ "Open-weights / fine-tuning", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "5+ window commits (12)", "+0.2" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 319, "is_new": false, "commits_delta": 12, "rank_delta": 198, "commits_delta_last_run": 0 }, { "full_name": "Vaibhav-CD/SmartINK", "html_url": "https://github.com/Vaibhav-CD/SmartINK", "track": "Build for Your World", "domain": "Education & Knowledge Systems", "summary": "Infinite canvas notebook with inking, live math, PDF studio and AI research copilot.", "readme_summary": "Spatial infinite-canvas notebook with pen smoothing, zoom and minimap, living calculations, and multilingual PDF reading with voice. Built with React Vite Tailwind and powered by Meta multimodal models for research assistance.", "tech_highlights": [ "Meta Multimodal AI", "React + Vite", "Infinite Canvas" ], "created_at": "2026-10-29T07:36:44Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 12, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": true, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": true, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.8, "score_meta_tooling": 2.3, "score_tech_depth": 0.8, "score_demo": 1.0, "score_total": 5.9, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ], [ "Open-weights / fine-tuning", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "5+ window commits (12)", "+0.2" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 320, "is_new": true, "commits_delta": 12, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "Ayushichadha/meta-autonomous-lab", "html_url": "https://github.com/Ayushichadha/meta-autonomous-lab", "track": "Push the Frontier", "domain": "Robotics, IoT & Manufacturing", "summary": "Simulates factory outages and tests PERSIST or REPLAN recovery strategies.", "readme_summary": "Simulation-grounded digital twin with 4 machines and 8 orders, modeling outages and rerouting. Muse Spark 1.3 proposes bounded experiments, compares evidence and selects recovery action.", "tech_highlights": [ "Muse Spark 1.3", "Digital Twin Sim", "Python + Configs" ], "created_at": "2026-10-30T17:49:42Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 9, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": true, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.3, "score_meta_tooling": 1.3, "score_tech_depth": 1.3, "score_demo": 1.0, "score_total": 5.9, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "High-impact domain", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "5+ window commits (9)", "+0.2" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Automated CI workflow", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 321, "is_new": true, "commits_delta": 9, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "chidibede/sitesentinel", "html_url": "https://github.com/chidibede/sitesentinel", "track": "Build for Your World", "domain": "Multimodal Vision & Video (SAM / Vision)", "summary": "Live worksite safety monitor detecting PPE violations from video streams", "readme_summary": "Agentic monitoring for construction and factory sites ingesting Ray-Ban glasses and phone video. SAM 3.1 segments people and hazards, Muse Spark reasons against safety manuals. AWS serverless stack with voice alerts and fix verification.", "tech_highlights": [ "SAM 3.1 Vision", "Muse Spark Reasoning", "AWS Lambda + SST" ], "created_at": "2026-10-27T18:43:28Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 6, "commits_before_window": 0, "prs_total": 2, "prs_merged": 2, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": true, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": true, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.8, "score_meta_tooling": 2.3, "score_tech_depth": 0.8, "score_demo": 1.0, "score_total": 5.9, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ], [ "Open-weights / fine-tuning", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "5+ window commits (6)", "+0.2" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 322, "is_new": false, "commits_delta": 0, "rank_delta": -185, "commits_delta_last_run": 0 }, { "full_name": "iamsourabhraikwar/meta-global-ai-developer-hackathon-2026", "html_url": "https://github.com/iamsourabhraikwar/meta-global-ai-developer-hackathon-2026", "track": "Build for Your World", "domain": "Multimodal Vision & Video (SAM / Vision)", "summary": "Autonomous CCTV operator that detects incidents and alerts via WhatsApp", "readme_summary": "Monitors live CCTV streams, detects motion in watch zones, extracts text/plates, validates with Muse Spark Open 1026 and SAM 3.1 segmentation. Next.js 14 frontend with WhatsApp Cloud API alerts.", "tech_highlights": [ "Muse Spark Open", "SAM 3.1 Vision", "Next.js + WhatsApp" ], "created_at": "2026-10-30T16:27:23Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 5, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": true, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": true, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 1, "score_impact": 1.8, "score_meta_tooling": 2.3, "score_tech_depth": 0.8, "score_demo": 1.0, "score_total": 5.9, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ], [ "Open-weights / fine-tuning", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "5+ window commits (5)", "+0.2" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 323, "is_new": true, "commits_delta": 5, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "smellak/gifford", "html_url": "https://github.com/smellak/gifford", "track": "Push the Frontier", "domain": "Developer Tooling, Infra & Security", "summary": "Lets coding agents message each other without typing over the human", "readme_summary": "PTY proxy for interactive coding agents like Muse Code, Codex and Claude Code. Deterministic guards control delivery and Muse Glimmer judges readiness. Built openly by multi-harness agents.", "tech_highlights": [ "Muse Glimmer", "PTY Proxy + Go", "Guarded Messaging" ], "created_at": "2026-10-28T11:34:44Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 1118, "commits_before_window": 0, "prs_total": 298, "prs_merged": 279, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": true, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": true, "has_eval_benchmarks": false, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.3, "score_meta_tooling": 1.0, "score_tech_depth": 1.9, "score_demo": 0.6, "score_total": 5.8, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "High-impact domain", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Open-weights / fine-tuning", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (1118)", "+0.6" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Automated CI workflow", "+0.2" ], [ "PR review workflow (279 PRs)", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 324, "is_new": true, "commits_delta": 1118, "rank_delta": 0, "commits_delta_last_run": 13 }, { "full_name": "lavenhill/baby-bust", "html_url": "https://github.com/lavenhill/baby-bust", "track": "Build for Your World", "domain": "Gaming, Entertainment & Creative Media", "summary": "Bilingual story game about Taiwan family policy and photo framing", "readme_summary": "Baby Bust is a short bilingual browser story game where you run social media for a government office and publish only half a photo yearly 2018-2026. Static HTML/JS with Meta Muse models used in development, mobile-friendly with demo video.", "tech_highlights": [ "Static HTML/JS game", "Meta Muse models", "Bilingual EN + zh-TW" ], "created_at": "2026-10-26T23:06:21Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 550, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": false, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": false, "has_video_demo": true, "video_urls": [ "https://www.youtube.com/watch?v=BsaZO8jI170", "https://www.youtube.com/watch?v=DKzJTC6pexk" ], "has_live_deploy": true, "live_urls": [ "https://lavenhill.github.io/baby-bust/" ], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.7, "score_meta_tooling": 1.1, "score_tech_depth": 0.9, "score_demo": 2.1, "score_total": 5.8, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "General domain", "+0.2" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (550)", "+0.6" ] ], "demo": [ [ "Base", "+0.4" ], [ "Video walkthrough", "+1.1" ], [ "Live web deployment", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 325, "is_new": true, "commits_delta": 550, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "felixgabriel94/hireMarco", "html_url": "https://github.com/felixgabriel94/hireMarco", "track": "Build for Your World", "domain": "Autonomous Agents & Workflow Automation", "summary": "Text-based AI COO on WhatsApp that runs recording sessions and daily ops", "readme_summary": "WhatsApp operator for an artist handles voice session control, email, phone booking and proofs. Brain is Muse Spark on Meta Model API with a gate plus Muse Wonder critic against RULES.md. Built for Build for Your World indie track.", "tech_highlights": [ "Muse Spark", "Muse Wonder Critic", "WhatsApp + Voice" ], "created_at": "2026-10-28T06:21:12Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 276, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 1, "score_impact": 1.9, "score_meta_tooling": 1.8, "score_tech_depth": 1.5, "score_demo": 0.6, "score_total": 5.8, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "High-impact domain", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (276)", "+0.6" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 326, "is_new": false, "commits_delta": 141, "rank_delta": -280, "commits_delta_last_run": 4 }, { "full_name": "iggykimi/bidlab", "html_url": "https://github.com/iggykimi/bidlab", "track": "Build for Your World", "domain": "Legal & Compliance", "summary": "Turns Spanish tender PDFs into defensible bid prices with citations", "readme_summary": "Local-first assistant where Muse Spark extracts requirements with page citations for human approval. Deterministic Python engine computes price, points and low-offer rules with accessible Spanish voice UI.", "tech_highlights": [ "Muse Spark", "Deterministic Pricing", "Accessible Spanish UI" ], "created_at": "2026-10-26T19:12:09Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 184, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": true, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.8, "score_meta_tooling": 1.3, "score_tech_depth": 1.7, "score_demo": 1.0, "score_total": 5.8, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (184)", "+0.6" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Automated CI workflow", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 327, "is_new": false, "commits_delta": 76, "rank_delta": -170, "commits_delta_last_run": 0 }, { "full_name": "heynomads/elynd-worlds", "html_url": "https://github.com/heynomads/elynd-worlds", "track": "Build for Your World", "domain": "Gaming, Entertainment & Creative Media", "summary": "Generates a living painted world animation for each guided meditation", "readme_summary": "Library of 445 painted scenes plus live generation for personal meditations, animated to loop seamlessly. Python plus Flutter and web viewers. Uses Meta models to design, paint, check, and animate worlds.", "tech_highlights": [ "Meta Image Models", "Generative Animation", "Flutter + Python" ], "created_at": "2026-10-28T10:43:32Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 134, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": true, "live_urls": [ "https://heynomads.github.io/elynd-worlds/web/**,", "https://heynomads.github.io/elynd-worlds/web/," ], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.7, "score_meta_tooling": 1.6, "score_tech_depth": 1.5, "score_demo": 1.0, "score_total": 5.8, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "General domain", "+0.2" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (134)", "+0.6" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Live web deployment", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 328, "is_new": false, "commits_delta": 53, "rank_delta": -246, "commits_delta_last_run": 0 }, { "full_name": "NayilRArana/primordial-paradox", "html_url": "https://github.com/NayilRArana/primordial-paradox", "track": "Build for Your World", "domain": "Gaming, Entertainment & Creative Media", "summary": "Retro NES RPG about Greek gods where you win battles by speaking persuasive replies", "readme_summary": "GameMaker RPG at 256x240 with NES palette constraints where typed or spoken dialogue drives battles and mercy meter. Uses Meta models via local bridge with Muse Glimmer and replay cache for dialogue and pipeline enforcement.", "tech_highlights": [ "Muse Glimmer", "GameMaker 256x240 NES", "Voice Dialogue System" ], "created_at": "2026-10-26T17:05:23Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 127, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": false, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": true, "has_eval_benchmarks": false, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.7, "score_meta_tooling": 2.3, "score_tech_depth": 1.2, "score_demo": 0.6, "score_total": 5.8, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "General domain", "+0.2" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ], [ "Open-weights / fine-tuning", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (127)", "+0.6" ], [ "Automated test suite", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 329, "is_new": false, "commits_delta": 10, "rank_delta": -250, "commits_delta_last_run": 0 }, { "full_name": "pettigrewlabllc/playtest-watcher", "html_url": "https://github.com/pettigrewlabllc/playtest-watcher", "track": "Build for Your World", "domain": "Gaming, Entertainment & Creative Media", "summary": "Syncs kid playtest face, voice and game events to find fun-killing moments", "readme_summary": "Watches real playtests by syncing face, hands, voice, screen and Godot event logs, then generates fix lists and persona testers. Node.js + Godot harness with results viewer. Uses Meta models for affect analysis and reaction prediction.", "tech_highlights": [ "Meta Models", "Godot + Node.js", "Multimodal Sync" ], "created_at": "2026-10-27T21:27:33Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 121, "commits_before_window": 0, "prs_total": 2, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.7, "score_meta_tooling": 1.6, "score_tech_depth": 1.5, "score_demo": 1.0, "score_total": 5.8, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "General domain", "+0.2" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (121)", "+0.6" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 330, "is_new": false, "commits_delta": 48, "rank_delta": -44, "commits_delta_last_run": 3 }, { "full_name": "Lembergdk/hygge", "html_url": "https://github.com/Lembergdk/hygge", "track": "Build for Your World", "domain": "Business, Sales & Commerce", "summary": "Cozy gig-work app that finds jobs and manages bookings and calendar", "readme_summary": "iOS Swift app with Python backend that aggregates gig listings and automates managing work. Built for Build for Your World with calendar, bookings and messaging to reduce unpaid job-hunt work.", "tech_highlights": [ "Swift + Xcode", "Python Backend", "Gig Aggregation" ], "created_at": "2026-10-30T22:17:22Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 58, "commits_before_window": 0, "prs_total": 8, "prs_merged": 7, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": true, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": true, "live_urls": [ "https://usehygge.app" ], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 1, "score_impact": 1.8, "score_meta_tooling": 1.1, "score_tech_depth": 1.9, "score_demo": 1.0, "score_total": 5.8, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (58)", "+0.6" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Automated CI workflow", "+0.2" ], [ "PR review workflow (7 PRs)", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Live web deployment", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 331, "is_new": true, "commits_delta": 58, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "shaikh-amer/Robolance", "html_url": "https://github.com/shaikh-amer/Robolance", "track": "Push the Frontier", "domain": "Robotics, IoT & Manufacturing", "summary": "Phone app where you describe robot tasks and AI codes and trains firmware", "readme_summary": "Plain-language to robot pipeline that writes firmware, runs MuJoCo physics sim and trains on cloud GPUs. Uses Meta-powered agent with Modal, Baseten and Fireworks for iterative fix-until-works loop.", "tech_highlights": [ "MuJoCo Physics Sim", "Meta Agent + GPUs", "Modal + Baseten" ], "created_at": "2026-10-26T17:54:05Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 55, "commits_before_window": 0, "prs_total": 54, "prs_merged": 54, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": true, "has_ci": true, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": true, "live_urls": [ "https://robolance.openlance.ai/runs/" ], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 1, "score_impact": 2.1, "score_meta_tooling": 1.1, "score_tech_depth": 1.6, "score_demo": 1.0, "score_total": 5.8, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "High-impact domain", "+0.4" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (55)", "+0.6" ], [ "Modular src/ architecture", "+0.3" ], [ "Automated CI workflow", "+0.2" ], [ "PR review workflow (54 PRs)", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Live web deployment", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 332, "is_new": true, "commits_delta": 55, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "AdvayGujar/pixelphysicist", "html_url": "https://github.com/AdvayGujar/pixelphysicist", "track": "Push the Frontier", "domain": "Multimodal Vision & Video (SAM / Vision)", "summary": "Turns phone video of motion into tested physics equations", "readme_summary": "SAM 3.1 tracks objects to position curves, classical code fits textbook equations. Muse Spark proposes missing physics from residuals; refit must beat baseline on held-out footage. Python pipeline with pinned results docs.", "tech_highlights": [ "SAM 3.1 Tracking", "Muse Spark Physics", "Python + Held-out Eval" ], "created_at": "2026-10-27T16:41:27Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 53, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.2, "score_meta_tooling": 1.1, "score_tech_depth": 1.5, "score_demo": 1.0, "score_total": 5.8, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "Domain alignment", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (53)", "+0.6" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 333, "is_new": false, "commits_delta": 12, "rank_delta": -203, "commits_delta_last_run": 0 }, { "full_name": "inventor1975/ztl-engineer", "html_url": "https://github.com/inventor1975/ztl-engineer", "track": "Push the Frontier", "domain": "Robotics, IoT & Manufacturing", "summary": "Verifies engineering designs from photos and datasheets with earned or refuted proofs", "readme_summary": "ZTL Engineer turns phone photos of nameplates, datasheets and CAD into formal design bricks and proves EARNED/REFUTED/OPEN. Python server + web UI with MCP server. Uses Muse Spark via Responses API function calling to build and self-repair bricks.", "tech_highlights": [ "Muse Spark", "Responses Function Call", "MCP Server + Python" ], "created_at": "2026-10-26T16:27:44Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 50, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": false, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": false, "has_video_demo": true, "video_urls": [ "https://youtu.be/a8-cb6Ng4-g" ], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.1, "score_meta_tooling": 1.3, "score_tech_depth": 0.9, "score_demo": 1.5, "score_total": 5.8, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "High-impact domain", "+0.4" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (50)", "+0.6" ] ], "demo": [ [ "Base", "+0.4" ], [ "Video walkthrough", "+1.1" ] ] }, "rank": 334, "is_new": false, "commits_delta": 2, "rank_delta": -231, "commits_delta_last_run": 0 }, { "full_name": "aaron202010/hackathon-frontdesk-meta", "html_url": "https://github.com/aaron202010/hackathon-frontdesk-meta", "track": "Build for Your World", "domain": "Healthcare, Civic Tech & Sustainability", "summary": "After-hours dental clinic agent that reads HMO cards, checks coverage and books.", "readme_summary": "Answers patient chats from clinic facts, parses HMO card photos and voice notes, then offers only open slots for booking. Python app with staff handoff and medical-query guardrails. Uses SAM 3.1 for card vision and Muse Spark for dialogue.", "tech_highlights": [ "SAM 3.1 Vision", "Muse Spark 1.3", "Messenger Booking" ], "created_at": "2026-10-26T18:30:45Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 43, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": true, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.2, "score_meta_tooling": 1.3, "score_tech_depth": 1.5, "score_demo": 0.8, "score_total": 5.8, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "High-impact domain", "+0.4" ], [ "Eval & benchmark proof", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (43)", "+0.4" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Agent / eval harness", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ] ] }, "rank": 335, "is_new": false, "commits_delta": 1, "rank_delta": -168, "commits_delta_last_run": 0 }, { "full_name": "minasami/pharmacy-stock-agent", "html_url": "https://github.com/minasami/pharmacy-stock-agent", "track": "Build for Your World", "domain": "Healthcare, Civic Tech & Sustainability", "summary": "Scans pharmacy shelf photos to read packs, flag expiry, and draft restock orders", "readme_summary": "Pharmacist photographs shelf or delivery carton; SAM 3.1 segments medicine boxes then Muse Spark extracts structured data. Matches catalog, flags expired and near-expiry lots, and proposes approval-gated stock actions. Human-in-loop with audit log for low-confidence reads.", "tech_highlights": [ "SAM 3.1 Vision", "Muse Spark 1.3", "Human-in-loop" ], "created_at": "2026-10-27T13:56:50Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 38, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.9, "score_meta_tooling": 1.6, "score_tech_depth": 1.3, "score_demo": 1.0, "score_total": 5.8, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "High-impact domain", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (38)", "+0.4" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 336, "is_new": false, "commits_delta": 0, "rank_delta": -265, "commits_delta_last_run": 0 }, { "full_name": "libertyfidja-bit/kuracommerce-meta", "html_url": "https://github.com/libertyfidja-bit/kuracommerce-meta", "track": "Build for Your World", "domain": "Business, Sales & Commerce", "summary": "Photo-to-listing commerce studio creating trilingual WhatsApp ads for vendors", "readme_summary": "For Rwandan micro-merchants, photo and voice input becomes priced Kinyarwanda-English-French WhatsApp listing pinned on map. SAM 3.1 segments product, Muse Wonder extracts title and price, Muse Image enhances photo, Muse Spark writes copy.", "tech_highlights": [ "SAM 3.1 Segmentation", "Muse Wonder", "Muse Image + Spark" ], "created_at": "2026-10-27T22:02:48Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 36, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": true, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": true, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": true, "live_urls": [ "https://kuracommerce-meta.onrender.com" ], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.3, "score_meta_tooling": 2.3, "score_tech_depth": 1.0, "score_demo": 1.2, "score_total": 5.8, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ], [ "Open-weights / fine-tuning", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (36)", "+0.4" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Live web deployment", "+0.4" ] ] }, "rank": 337, "is_new": false, "commits_delta": 21, "rank_delta": -48, "commits_delta_last_run": 0 }, { "full_name": "andrice90/mibo", "html_url": "https://github.com/andrice90/mibo", "track": "Build for Your World", "domain": "Voice, Speech & Audio AI", "summary": "Friendly character leads short daily speech practice for families at home", "readme_summary": "Mibo is an iOS app where an animated blob models sounds with exaggerated mouth shapes for kids practice. Built with Swift + tools/evals, it uses Meta models for lesson guidance and progress ideas, non-diagnostic.", "tech_highlights": [ "Meta AI Models", "iOS Swift App", "Speech Practice" ], "created_at": "2026-10-27T02:02:13Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 27, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": true, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.1, "score_meta_tooling": 1.8, "score_tech_depth": 1.5, "score_demo": 0.4, "score_total": 5.8, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Eval & benchmark proof", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (27)", "+0.4" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Agent / eval harness", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ] ] }, "rank": 338, "is_new": true, "commits_delta": 27, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "Shaurya-flex/Seat-desk", "html_url": "https://github.com/Shaurya-flex/Seat-desk", "track": "Build for Your World", "domain": "Business, Sales & Commerce", "summary": "Hindi/English shop assistant answering only from cited approved policies", "readme_summary": "Answers enquiries only from approved business info with citations, uses deterministic seat-availability engine and human handoff. Python workflow with mock model adapter, tests and evals included.", "tech_highlights": [ "Cited Retrieval", "Deterministic Engine", "Python + Evals" ], "created_at": "2026-11-01T05:47:56Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 25, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": true, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": true, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.1, "score_meta_tooling": 1.0, "score_tech_depth": 1.7, "score_demo": 1.0, "score_total": 5.8, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Eval & benchmark proof", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (25)", "+0.4" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Agent / eval harness", "+0.2" ], [ "Automated CI workflow", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 339, "is_new": true, "commits_delta": 25, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "asiyetajwa/consumed", "html_url": "https://github.com/asiyetajwa/consumed", "track": "Build for Your World", "domain": "Gaming, Entertainment & Creative Media", "summary": "Daily visual diary that logs what you consume and repaints it as shareable art", "readme_summary": "Consumed logs meals, books and music by photo or search into one daily page. Muse Spark extracts structured item JSON and Muse Image repaints entries in gouache style for a social feed and sealed daily capsule.", "tech_highlights": [ "Muse Spark 1.3", "Muse Image", "Next.js + TypeScript" ], "created_at": "2026-10-26T17:25:17Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 22, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.7, "score_meta_tooling": 1.8, "score_tech_depth": 1.3, "score_demo": 1.0, "score_total": 5.8, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "General domain", "+0.2" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (22)", "+0.4" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 340, "is_new": false, "commits_delta": 0, "rank_delta": -308, "commits_delta_last_run": 0 }, { "full_name": "vonnue-akhil/SecondLife-AI", "html_url": "https://github.com/vonnue-akhil/SecondLife-AI", "track": "Build for Your World", "domain": "Healthcare, Civic Tech & Sustainability", "summary": "Multimodal assistant ranking repair, reuse, donate, resell or recycle options.", "readme_summary": "SecondLife AI takes device photos, clips or speech plus questions to give ranked reuse recommendations, safety guidance and India-focused resources. Client-server JS app with chat, safety layer and curated resources. Uses Muse Spark for reasoning, SAM 3.1 for damage highlight and Muse Voice Transcribe.", "tech_highlights": [ "Muse Spark 1.3", "SAM 3.1 Vision", "Muse Voice Transcribe" ], "created_at": "2026-10-28T06:16:53Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 8, "commits_before_window": 0, "prs_total": 2, "prs_merged": 2, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": true, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": true, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.7, "score_meta_tooling": 2.3, "score_tech_depth": 0.8, "score_demo": 1.0, "score_total": 5.8, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "High-impact domain", "+0.4" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ], [ "Open-weights / fine-tuning", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "5+ window commits (8)", "+0.2" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 341, "is_new": false, "commits_delta": 7, "rank_delta": 148, "commits_delta_last_run": 0 }, { "full_name": "dayplayTeam/dayplay-ar-hackathon", "html_url": "https://github.com/dayplayTeam/dayplay-ar-hackathon", "track": "Build for Your World", "domain": "Multimodal Vision & Video (SAM / Vision)", "summary": "AR corridor on Valencia St showing only verified real-world DayPlay pins", "readme_summary": "Renders verified DayPlay listings as bearing/distance placards in a walkable AR corridor with zero-hallucination invariant. Architecture is static FOV sim plus FastAPI backend with intent-to-pipeline for constrained listing retrieval. Model plans and parses queries but never invents places.", "tech_highlights": [ "FastAPI + Static Sim", "AR Spatial Pins", "Constrained Retrieval" ], "created_at": "2026-10-29T18:10:19Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 8, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": true, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.9, "score_meta_tooling": 1.6, "score_tech_depth": 1.3, "score_demo": 1.0, "score_total": 5.8, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Eval & benchmark proof", "+0.3" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "5+ window commits (8)", "+0.2" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Agent / eval harness", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 342, "is_new": true, "commits_delta": 8, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "waleedmustafa971/forge-0-core", "html_url": "https://github.com/waleedmustafa971/forge-0-core", "track": "Push the Frontier", "domain": "Developer Tooling, Infra & Security", "summary": "Evidence-driven debugging agent that tests hypotheses in Docker sandbox", "readme_summary": "Autonomous debugger that generates hypotheses, runs discriminating experiments in isolated Docker, and proposes patches only after independent verifier approval. Targets Muse Spark 1.3 via Meta Model API, mock mode now.", "tech_highlights": [ "Muse Spark 1.3", "Docker Sandbox", "Verifier Agent" ], "created_at": "2026-10-28T04:35:59Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 1, "commits_before_window": 1, "prs_total": 0, "prs_merged": 0, "is_preexisting": true, "has_docker": true, "has_tests": false, "has_src": true, "has_ci": true, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": true, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 3.0, "score_meta_tooling": 1.3, "score_tech_depth": 0.5, "score_demo": 1.0, "score_total": 5.8, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "High-impact domain", "+0.4" ], [ "Eval & benchmark proof", "+0.3" ], [ "Docker packaging", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Agent / eval harness", "+0.2" ], [ "Automated CI workflow", "+0.2" ], [ "Pre-existing repo (<=2 commits)", "-0.5" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 343, "is_new": false, "commits_delta": 0, "rank_delta": -217, "commits_delta_last_run": 0 }, { "full_name": "oneiron-dev/muse-glimmer-afterglow", "html_url": "https://github.com/oneiron-dev/muse-glimmer-afterglow", "track": "Push the Frontier", "domain": "Developer Tooling, Infra & Security", "summary": "Local Muse Glimmer that trains nightly QLoRA adapters from daily notes", "readme_summary": "Afterglow runs Muse Glimmer 30B on local GPU as daytime agent with notes. A nightly job turns the day into training data, trains QLoRA on same GPU, tests against held-out and general skills, keeping updates only without forgetting.", "tech_highlights": [ "Muse Glimmer 30B", "QLoRA nightly training", "llama.cpp + DFlash" ], "created_at": "2026-10-26T19:37:53Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 654, "commits_before_window": 0, "prs_total": 143, "prs_merged": 143, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": true, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": true, "has_eval_benchmarks": true, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.3, "score_meta_tooling": 1.0, "score_tech_depth": 1.6, "score_demo": 0.8, "score_total": 5.7, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "High-impact domain", "+0.4" ], [ "Eval & benchmark proof", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ] ], "meta": [ [ "Base", "+0.5" ], [ "Open-weights / fine-tuning", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (654)", "+0.6" ], [ "Modular src/ architecture", "+0.3" ], [ "Agent / eval harness", "+0.2" ], [ "PR review workflow (143 PRs)", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ] ] }, "rank": 344, "is_new": false, "commits_delta": 225, "rank_delta": -13, "commits_delta_last_run": 0 }, { "full_name": "Kunal-Shahi/shipcube", "html_url": "https://github.com/Kunal-Shahi/shipcube", "track": "Push the Frontier", "domain": "Developer Tooling, Infra & Security", "summary": "MCP infrastructure layer to size, deploy and govern agent-built apps on GCP", "readme_summary": "Infrastructure layer for apps built with coding agents via MCP server. Handles load estimation, caps, deployment to Cloud Run/GKE, access control and data layer. Provides AI gateway for apps needing models.", "tech_highlights": [ "MCP Server", "GCP Cloud Run + GKE", "AI Gateway" ], "created_at": "2026-10-27T12:06:17Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 434, "commits_before_window": 0, "prs_total": 88, "prs_merged": 86, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": true, "has_ci": true, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": true, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.3, "score_meta_tooling": 0.8, "score_tech_depth": 1.8, "score_demo": 0.8, "score_total": 5.7, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "High-impact domain", "+0.4" ], [ "Eval & benchmark proof", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ] ], "meta": [ [ "Base", "+0.5" ], [ "Muse Spark integration", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (434)", "+0.6" ], [ "Modular src/ architecture", "+0.3" ], [ "Agent / eval harness", "+0.2" ], [ "Automated CI workflow", "+0.2" ], [ "PR review workflow (86 PRs)", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ] ] }, "rank": 345, "is_new": true, "commits_delta": 434, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "annatchijova/krakadyl", "html_url": "https://github.com/annatchijova/krakadyl", "track": "Build for Your World", "domain": "Legal & Compliance", "summary": "Coordinates forensic investigations and flags missing verifiable evidence early", "readme_summary": "KRAKADYL organizes cases, tracks mandate limits and proposes next verifiable investigative steps. It leaves conclusions to inference tools and human investigators. Built with Python backend, frontend and investigation tools for time-pressured forensic work.", "tech_highlights": [ "Muse Spark", "Python Agent", "Forensic Workflow" ], "created_at": "2026-10-27T13:14:41Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 204, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": true, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.8, "score_meta_tooling": 1.6, "score_tech_depth": 1.7, "score_demo": 0.6, "score_total": 5.7, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (204)", "+0.6" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Automated CI workflow", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 346, "is_new": false, "commits_delta": 160, "rank_delta": -276, "commits_delta_last_run": 0 }, { "full_name": "jckjjcckk/folio-pad", "html_url": "https://github.com/jckjjcckk/folio-pad", "track": "Build for Your World", "domain": "Education & Knowledge Systems", "summary": "AI score librarian that splits parts to iPads and syncs conductor marks live", "readme_summary": "Scans or imports scores, detects systems and bars, names parts, cuts per-player parts and converts scans to notation. Conductor voice notes become proposed marks, marks sync live across stands, parts play back for practice. Web app plus TestFlight iPad app.", "tech_highlights": [ "OMR Score Vision", "Supabase Realtime", "Voice-to-Mark" ], "created_at": "2026-10-26T18:53:15Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 196, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": false, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": true, "live_urls": [ "https://tonejs.github.io" ], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.6, "score_meta_tooling": 1.8, "score_tech_depth": 0.9, "score_demo": 1.4, "score_total": 5.7, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (196)", "+0.6" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Live web deployment", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 347, "is_new": false, "commits_delta": 70, "rank_delta": -94, "commits_delta_last_run": 0 }, { "full_name": "sabr2007/meta-global-hackathon", "html_url": "https://github.com/sabr2007/meta-global-hackathon", "track": "Push the Frontier", "domain": "Robotics, IoT & Manufacturing", "summary": "Generates an approved after-photo of a tidy table and executes it with robots", "readme_summary": "AYNA takes a spoken tidy request and current table photo, generates a verified after photo with Muse Image checked by SAM 3.1, converts it to centimetre goals, and executes in a physics twin. Returns a receipt of final object positions.", "tech_highlights": [ "Muse Image Gen", "SAM 3.1 Verify", "Physics Twin Sim" ], "created_at": "2026-10-26T22:46:39Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 152, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": false, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": true, "live_urls": [ "https://ayna-brown.vercel.app/app/", "https://ayna-brown.vercel.app/", "https://ayna-brown.vercel.app/app/?autoplay", "https://ayna-brown.vercel.app/app/#/scan/f5757ba8142d/desk-sam3d/run/20261029-050201-yea3", "https://ayna-brown.vercel.app/app/#/scan/f5757ba8142d/desk-sam3d/run/20261029-050808-tj09", "https://ayna-scan.vercel.app" ], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.1, "score_meta_tooling": 1.3, "score_tech_depth": 0.9, "score_demo": 1.4, "score_total": 5.7, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "High-impact domain", "+0.4" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (152)", "+0.6" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Live web deployment", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 348, "is_new": false, "commits_delta": 151, "rank_delta": -49, "commits_delta_last_run": 0 }, { "full_name": "jerrydjin/backtothefuture", "html_url": "https://github.com/jerrydjin/backtothefuture", "track": "Push the Frontier", "domain": "Autonomous Agents & Workflow Automation", "summary": "Rust agent harness simulating traffic priority and hospital routing decisions.", "readme_summary": "Muse is a Rust agent harness demoing traffic decisions on a continuous road network. Supports live, mock and replay modes with decision logs and recordings. Uses Baseten-hosted live model with scripted fallback without key.", "tech_highlights": [ "Rust Agent Harness", "Replay + Scoring", "Baseten Live Model" ], "created_at": "2026-10-26T18:04:05Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 142, "commits_before_window": 0, "prs_total": 42, "prs_merged": 40, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": true, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.3, "score_meta_tooling": 0.5, "score_tech_depth": 1.9, "score_demo": 1.0, "score_total": 5.7, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "High-impact domain", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (142)", "+0.6" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Automated CI workflow", "+0.2" ], [ "PR review workflow (40 PRs)", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 349, "is_new": false, "commits_delta": 133, "rank_delta": 12, "commits_delta_last_run": 0 }, { "full_name": "jerrydjin/malleable", "html_url": "https://github.com/jerrydjin/malleable", "track": "Push the Frontier", "domain": "Autonomous Agents & Workflow Automation", "summary": "Rust agent harness simulating priority traffic decisions with live or mock policy", "readme_summary": "Rust harness formerly backtothefuture/muse for scenario demos like rush-hour and hospital priority. CLI with board, replay, scoring and decision logs. Uses live model via BASETEN_API_KEY with scripted fallback.", "tech_highlights": [ "Rust Agent Harness", "Scenario Replay", "Baseten Live Model" ], "created_at": "2026-10-26T18:04:05Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 142, "commits_before_window": 0, "prs_total": 42, "prs_merged": 40, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": true, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.3, "score_meta_tooling": 0.5, "score_tech_depth": 1.9, "score_demo": 1.0, "score_total": 5.7, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "High-impact domain", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (142)", "+0.6" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Automated CI workflow", "+0.2" ], [ "PR review workflow (40 PRs)", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 350, "is_new": true, "commits_delta": 142, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "BbekShr/pixypup", "html_url": "https://github.com/BbekShr/pixypup", "track": "Build for Your World", "domain": "Gaming, Entertainment & Creative Media", "summary": "Turns one pet photo into a desktop 3D companion that reacts to your work", "readme_summary": "PixyPup converts a single dog/cat photo into an Electron desktop companion that trots, does tricks, and flags failing tests. Built with Electron + Vite, TypeScript, and native modules. Uses Meta AI vision models for pet reconstruction and animation.", "tech_highlights": [ "Electron + Vite", "TypeScript", "Meta Vision AI" ], "created_at": "2026-11-01T02:28:47Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 139, "commits_before_window": 0, "prs_total": 41, "prs_merged": 40, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": true, "live_urls": [ "https://bbekshr.github.io/pixypup/" ], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.7, "score_meta_tooling": 1.3, "score_tech_depth": 1.7, "score_demo": 1.0, "score_total": 5.7, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "General domain", "+0.2" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (139)", "+0.6" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "PR review workflow (40 PRs)", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Live web deployment", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 351, "is_new": true, "commits_delta": 139, "rank_delta": 0, "commits_delta_last_run": 39 }, { "full_name": "Esteban9427/climapp-lite", "html_url": "https://github.com/Esteban9427/climapp-lite", "track": "Build for Your World", "domain": "Healthcare, Civic Tech & Sustainability", "summary": "Daily heavy-rain forecast for Rio Pance with citizen photo confirmations", "readme_summary": "Publishes daily probability of 20mm+ rain for Pance basin plus 3-day landslide signal for visitors. Python stack with verifiable code-scored confirmations. Muse Spark structures reports and explains forecasts in plain language.", "tech_highlights": [ "Muse Spark", "Python + FastAPI", "Hydroclimate Data" ], "created_at": "2026-10-29T21:53:38Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 128, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.9, "score_meta_tooling": 1.3, "score_tech_depth": 1.5, "score_demo": 1.0, "score_total": 5.7, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "High-impact domain", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (128)", "+0.6" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 352, "is_new": true, "commits_delta": 128, "rank_delta": 0, "commits_delta_last_run": 19 }, { "full_name": "mackmind/piccompare-aec-agent", "html_url": "https://github.com/mackmind/piccompare-aec-agent", "track": "Build for Your World", "domain": "Autonomous Agents & Workflow Automation", "summary": "Floor-plan checker that measures rooms across revisions with replayable proof", "readme_summary": "PicCompare AEC Agent measures and matches rooms across two plan versions, reporting changes only when verifiable. Python + MCP/skills architecture produces fingerprinted reports for re-run verification.", "tech_highlights": [ "Vision Measurement", "MCP Agent", "Replayable Reports" ], "created_at": "2026-10-26T23:39:57Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 115, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": true, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.9, "score_meta_tooling": 1.1, "score_tech_depth": 1.7, "score_demo": 1.0, "score_total": 5.7, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "High-impact domain", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (115)", "+0.6" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Automated CI workflow", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 353, "is_new": false, "commits_delta": 65, "rank_delta": -268, "commits_delta_last_run": 0 }, { "full_name": "sensei-hq/snap-to-make", "html_url": "https://github.com/sensei-hq/snap-to-make", "track": "Build for Your World", "domain": "Robotics, IoT & Manufacturing", "summary": "Snap a sketch, speak intent, get cut-ready laser designs", "readme_summary": "Voice-first workshop app measures objects from phone photos and generates joints, preview and G-code. Built for desktop laser/vinyl cutters with Supabase backend and cut simulation.", "tech_highlights": [ "Vision Measurement", "Voice-first Maker", "Laser G-code Gen" ], "created_at": "2026-10-27T22:37:37Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 96, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": true, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": true, "live_urls": [ "https://developers.cloudflare.com/workers/" ], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.7, "score_meta_tooling": 1.8, "score_tech_depth": 1.2, "score_demo": 1.0, "score_total": 5.7, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "High-impact domain", "+0.4" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (96)", "+0.6" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Live web deployment", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 354, "is_new": false, "commits_delta": 0, "rank_delta": -241, "commits_delta_last_run": 0 }, { "full_name": "sensei-hq/katachi", "html_url": "https://github.com/sensei-hq/katachi", "track": "Build for Your World", "domain": "Robotics, IoT & Manufacturing", "summary": "Snap a sketch and object, speak a request, get measured cut-ready laser design", "readme_summary": "Voice-first workshop buddy for laser and vinyl cutter owners. Measures objects from photos, traces sketches, designs jointed parts with preview and cut simulation. Uses Meta AI vision-language models for measurement and design via phone plus web app.", "tech_highlights": [ "Muse Vision", "Photo Measurement", "G-code Output" ], "created_at": "2026-10-27T22:37:37Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 96, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": true, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": true, "live_urls": [ "https://developers.cloudflare.com/workers/" ], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.7, "score_meta_tooling": 1.8, "score_tech_depth": 1.2, "score_demo": 1.0, "score_total": 5.7, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "High-impact domain", "+0.4" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (96)", "+0.6" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Live web deployment", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 355, "is_new": true, "commits_delta": 96, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "depapranata26/mejabahasa", "html_url": "https://github.com/depapranata26/mejabahasa", "track": "Build for Your World", "domain": "Business, Sales & Commerce", "summary": "QR table chat lets guests order in their language, synced to staff screens.", "readme_summary": "MejaBahasa provides guest chat via QR code with auto language detection and menu-stock validation. Stack includes Python backend, SQLite, staff and kitchen dashboards with 200 checks. Uses Meta AI for multilingual chat, voice and order reasoning.", "tech_highlights": [ "Multilingual Agent", "QR Guest Chat", "SQLite + Dashboards" ], "created_at": "2026-10-27T16:21:53Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 87, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": true, "has_tests": false, "has_src": true, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.2, "score_meta_tooling": 1.3, "score_tech_depth": 1.2, "score_demo": 1.0, "score_total": 5.7, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Docker packaging", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (87)", "+0.6" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 356, "is_new": false, "commits_delta": 5, "rank_delta": -257, "commits_delta_last_run": 0 }, { "full_name": "Hedgeling/hedgeling-meta-hackathon", "html_url": "https://github.com/Hedgeling/hedgeling-meta-hackathon", "track": "Push the Frontier", "domain": "Autonomous Agents & Workflow Automation", "summary": "Meta Responses integration with extraction-review-import agent workflow", "readme_summary": "Event-only repo adding Meta Responses integration to Hedgeling agent with verification harness and engine clients. Provides project-bound extraction to review to import with shared API/MCP actions and UI. Separates new code from pre-existing platform.", "tech_highlights": [ "Meta Responses API", "MCP Actions", "Verification Harness" ], "created_at": "2026-10-27T08:32:53Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 82, "commits_before_window": 0, "prs_total": 21, "prs_merged": 21, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": true, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.3, "score_meta_tooling": 0.5, "score_tech_depth": 1.9, "score_demo": 1.0, "score_total": 5.7, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "High-impact domain", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (82)", "+0.6" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Automated CI workflow", "+0.2" ], [ "PR review workflow (21 PRs)", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 357, "is_new": true, "commits_delta": 82, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "SMAJORG/smaj-verified-delegation", "html_url": "https://github.com/SMAJORG/smaj-verified-delegation", "track": "Push the Frontier", "domain": "Autonomous Agents & Workflow Automation", "summary": "Delegated task agent that verifies outcomes with proof receipts", "readme_summary": "Next.js agent turns authorized goals into bounded actions with idempotency, sessions and human approval. Backend validates model catalog then calls responses API. Uses muse-spark-1.3 for planning and execution.", "tech_highlights": [ "muse-spark-1.3", "Next.js Agent Backend", "Proof Receipts" ], "created_at": "2026-10-21T08:14:19Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 80, "commits_before_window": 1, "prs_total": 0, "prs_merged": 0, "is_preexisting": true, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": true, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": true, "live_urls": [ "https://smajorg.github.io/smaj-verified-delegation/" ], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 4, "score_impact": 2.0, "score_meta_tooling": 0.8, "score_tech_depth": 1.7, "score_demo": 1.2, "score_total": 5.7, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "High-impact domain", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ] ], "meta": [ [ "Base", "+0.5" ], [ "Muse Spark integration", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (80)", "+0.6" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Automated CI workflow", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Live web deployment", "+0.4" ] ] }, "rank": 358, "is_new": false, "commits_delta": 80, "rank_delta": 142, "commits_delta_last_run": 0 }, { "full_name": "Cole-Z/harbor-muse", "html_url": "https://github.com/Cole-Z/harbor-muse", "track": "Build for Your World", "domain": "General & Emerging Applications", "summary": "Live ship map where you can ask Muse about nearby vessels", "readme_summary": "One-page live tracker for US waters centered on user location. Uses aisstream.io AIS feed with MapLibre GL and OpenFreeMap. Muse models answer typed or dictated questions about visible ships.", "tech_highlights": [ "Muse Models", "MapLibre GL", "AIS Stream" ], "created_at": "2026-10-28T16:26:40Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 80, "commits_before_window": 0, "prs_total": 38, "prs_merged": 38, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": true, "live_urls": [ "https://cole-z.github.io/" ], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 1, "score_impact": 1.7, "score_meta_tooling": 1.1, "score_tech_depth": 1.7, "score_demo": 1.2, "score_total": 5.7, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "General domain", "+0.2" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (80)", "+0.6" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "PR review workflow (38 PRs)", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Live web deployment", "+0.4" ] ] }, "rank": 359, "is_new": false, "commits_delta": 66, "rank_delta": -14, "commits_delta_last_run": 2 }, { "full_name": "sitrsh12/meta-ai-hackathon-Aahwan_IT_Group", "html_url": "https://github.com/sitrsh12/meta-ai-hackathon-Aahwan_IT_Group", "track": "Build for Your World", "domain": "Voice, Speech & Audio AI", "summary": "Voice ordering agent for a Nepal pizzeria taking live phone orders", "readme_summary": "Production voice agent for PizzaGhar restaurant in Birtamode, Nepal. Node.js + web dashboard with Groq Whisper v3 for STT and Muse Spark 1.3 for conversational ordering. Handles live customer calls and owner order management.", "tech_highlights": [ "Muse Spark 1.3", "Groq Whisper v3", "Node.js + Express" ], "created_at": "2026-10-26T16:51:30Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 41, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": false, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": true, "video_urls": [ "https://www.youtube.com/watch?v=JlpBn9pfQHI" ], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.6, "score_meta_tooling": 1.3, "score_tech_depth": 0.7, "score_demo": 2.1, "score_total": 5.7, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (41)", "+0.4" ] ], "demo": [ [ "Base", "+0.4" ], [ "Video walkthrough", "+1.1" ], [ "Reproducible setup guide", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 360, "is_new": false, "commits_delta": 18, "rank_delta": -91, "commits_delta_last_run": 0 }, { "full_name": "aungsan-portfolio/meta-quant-auditor", "html_url": "https://github.com/aungsan-portfolio/meta-quant-auditor", "track": "Build for Your World", "domain": "Finance, Crypto & Web3", "summary": "Synthetic auditor showing why risk checks block trades with evidence comparison", "readme_summary": "Streamlit demo that reconstructs fictional trade timelines and audits quote-gate decisions. Local code validates actions while Muse Spark Open proposes claims for evidence comparison. Includes synthetic cases, tests and provenance docs.", "tech_highlights": [ "Muse Spark Open", "Streamlit + Python", "Baseten Deploy" ], "created_at": "2026-10-27T13:05:07Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 39, "commits_before_window": 0, "prs_total": 7, "prs_merged": 7, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": false, "has_ci": true, "meta_api_verified": false, "partner_infra": "Together", "open_weights_tuning": true, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.8, "score_meta_tooling": 1.5, "score_tech_depth": 1.4, "score_demo": 1.0, "score_total": 5.7, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "Partner inference infra", "+0.2" ], [ "Open-weights / fine-tuning", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (39)", "+0.4" ], [ "Automated test suite", "+0.3" ], [ "Automated CI workflow", "+0.2" ], [ "PR review workflow (7 PRs)", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 361, "is_new": false, "commits_delta": 27, "rank_delta": -118, "commits_delta_last_run": 0 }, { "full_name": "thekaifansari01/cortex-meta-agent", "html_url": "https://github.com/thekaifansari01/cortex-meta-agent", "track": "Push the Frontier", "domain": "Autonomous Agents & Workflow Automation", "summary": "Windows desktop agent that runs commands, files and messages", "readme_summary": "Open-source AI OS for Windows 10/11 that controls PC, runs terminal commands, manages files, and sends WhatsApp/Email. Python architecture with tools and memory powered by Muse Spark Open via Baseten inference.", "tech_highlights": [ "Muse Spark Open", "Baseten Inference", "Python Automation" ], "created_at": "2026-10-27T13:20:33Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 36, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": true, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": true, "has_eval_benchmarks": true, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.6, "score_meta_tooling": 1.3, "score_tech_depth": 1.2, "score_demo": 0.6, "score_total": 5.7, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "High-impact domain", "+0.4" ], [ "Eval & benchmark proof", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "Open-weights / fine-tuning", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (36)", "+0.4" ], [ "Modular src/ architecture", "+0.3" ], [ "Agent / eval harness", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 362, "is_new": false, "commits_delta": 7, "rank_delta": -150, "commits_delta_last_run": 0 }, { "full_name": "1jsjs/sourcenote", "html_url": "https://github.com/1jsjs/sourcenote", "track": "Build for Your World", "domain": "Education & Knowledge Systems", "summary": "Lecture notes agent that cites and verifies every claim from sources", "readme_summary": "Electron desktop app that transcribes lectures with Muse Voice Transcribe and summarizes with Muse Spark under strict JSON citation schema. Each sentence must cite audio timestamps or slide pages and is re-checked. Flags unsupported text as not in sources.", "tech_highlights": [ "Muse Spark 1.3", "Muse Voice Transcribe", "Electron + TypeScript" ], "created_at": "2026-10-27T05:40:47Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 36, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": true, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": true, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.1, "score_meta_tooling": 1.3, "score_tech_depth": 1.7, "score_demo": 0.6, "score_total": 5.7, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Eval & benchmark proof", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (36)", "+0.4" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Agent / eval harness", "+0.2" ], [ "Automated CI workflow", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 363, "is_new": false, "commits_delta": 7, "rank_delta": -150, "commits_delta_last_run": 0 }, { "full_name": "scrooksjr/Print3DFlow", "html_url": "https://github.com/scrooksjr/Print3DFlow", "track": "Build for Your World", "domain": "Robotics, IoT & Manufacturing", "summary": "3D-print shop workflow from customer request to quote and printer reservation", "readme_summary": "Manufacturing assistant for Print3DStore with Muse Spark intake, STL validation, mesh preview and Bambu Studio estimates. FastAPI backend plus frontend with approval-gated job creation and printer failover.", "tech_highlights": [ "Muse Spark", "FastAPI Backend", "Bambu Studio" ], "created_at": "2026-10-27T16:59:02Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 34, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": true, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.9, "score_meta_tooling": 1.3, "score_tech_depth": 1.5, "score_demo": 1.0, "score_total": 5.7, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "High-impact domain", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (34)", "+0.4" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Automated CI workflow", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 364, "is_new": true, "commits_delta": 34, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "limeric29/hubog-shoot", "html_url": "https://github.com/limeric29/hubog-shoot", "track": "Build for Your World", "domain": "Business, Sales & Commerce", "summary": "One phone photo becomes marketplace-ready listing photos and captions", "readme_summary": "Hubog Shoot for Philippine sellers takes one photo plus English/Filipino prompt. Muse Spark agent plans shoot, Muse Image renders packs, SAM 3.1 cleanup. Next.js + Modal stack, sized for Shopee/Lazada/TikTok.", "tech_highlights": [ "Muse Spark agent", "Muse Image render", "SAM 3.1 cleanup" ], "created_at": "2026-10-30T12:37:10Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 33, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.8, "score_meta_tooling": 1.8, "score_tech_depth": 1.3, "score_demo": 0.8, "score_total": 5.7, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (33)", "+0.4" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ] ] }, "rank": 365, "is_new": true, "commits_delta": 33, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "Nguyen-Le-Tuan/ScreenTutor", "html_url": "https://github.com/Nguyen-Le-Tuan/ScreenTutor", "track": "Build for Your World", "domain": "Education & Knowledge Systems", "summary": "Vietnamese on-screen tutor that guides new Windows users step by step", "readme_summary": "Windows assistant that combines screenshots with OS state sensors to teach while doing tasks. Modular Python with separate grounding, STT, TTS and tutor evals. Uses Muse Spark image understanding and Muse Voice Transcribe with local VieNeu-TTS.", "tech_highlights": [ "Muse Spark Vision", "Muse Voice STT", "VieNeu-TTS v3" ], "created_at": "2026-10-27T11:44:04Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 29, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": true, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 1, "score_impact": 2.1, "score_meta_tooling": 1.1, "score_tech_depth": 1.5, "score_demo": 1.0, "score_total": 5.7, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Eval & benchmark proof", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (29)", "+0.4" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Agent / eval harness", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 366, "is_new": true, "commits_delta": 29, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "khatabx-king/spiralai", "html_url": "https://github.com/khatabx-king/spiralai", "track": "Push the Frontier", "domain": "Autonomous Agents & Workflow Automation", "summary": "Physics-verified agent for graphene energy storage design exploration", "readme_summary": "Agent that proposes graphene designs with Muse Spark, then validates via deterministic physics and independent verifier. Includes benchmarks, provenance tracking, optimization and console UI with 47 tests passing.", "tech_highlights": [ "Muse Spark Open", "Physics Verification", "Python Agent" ], "created_at": "2026-10-27T06:27:17Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 22, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": false, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": true, "has_eval_benchmarks": true, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.6, "score_meta_tooling": 1.3, "score_tech_depth": 1.2, "score_demo": 0.6, "score_total": 5.7, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "High-impact domain", "+0.4" ], [ "Eval & benchmark proof", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "Open-weights / fine-tuning", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (22)", "+0.4" ], [ "Automated test suite", "+0.3" ], [ "Agent / eval harness", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 367, "is_new": true, "commits_delta": 22, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "seantw0301/safepath-ai", "html_url": "https://github.com/seantw0301/safepath-ai", "track": "Build for Your World", "domain": "Healthcare, Civic Tech & Sustainability", "summary": "Phone home scan that finds elder fall hazards and creates fix work orders", "readme_summary": "Elder home safety scanner: phone video sweep is segmented and measured by SAM 3.1, then an agent creates improvement work orders and subsidy drafts. Stack is PHP 8.3, MySQL, ffmpeg and Python samtool.", "tech_highlights": [ "SAM 3.1 Vision", "Muse Spark", "PHP + Python" ], "created_at": "2026-10-31T01:55:05Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 22, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": true, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.6, "score_meta_tooling": 1.8, "score_tech_depth": 1.5, "score_demo": 0.8, "score_total": 5.7, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "High-impact domain", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (22)", "+0.4" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Automated CI workflow", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ] ] }, "rank": 368, "is_new": true, "commits_delta": 22, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "yhyh4420/saferoute", "html_url": "https://github.com/yhyh4420/saferoute", "track": "Build for Your World", "domain": "Healthcare, Civic Tech & Sustainability", "summary": "Offline Android app giving hazard-specific evacuation routes in under a second.", "readme_summary": "SafeRoute shows where to walk by hazard type, earthquake vs flood, with no network using on-device maps and precomputed routes. Android app with pipeline and eval docs for Seoul shelters. Designed for Meta AI integration for guidance generation during the hackathon build.", "tech_highlights": [ "Offline Android", "On-device Routing", "Hazard Logic Engine" ], "created_at": "2026-10-28T00:11:11Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 15, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": true, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": true, "has_eval_benchmarks": true, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.0, "score_meta_tooling": 1.5, "score_tech_depth": 1.2, "score_demo": 1.0, "score_total": 5.7, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "High-impact domain", "+0.4" ], [ "Eval & benchmark proof", "+0.3" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ], [ "Open-weights / fine-tuning", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (15)", "+0.4" ], [ "Modular src/ architecture", "+0.3" ], [ "Agent / eval harness", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 369, "is_new": false, "commits_delta": 7, "rank_delta": -30, "commits_delta_last_run": 1 }, { "full_name": "alonsinhoiu/faro-rayosx-meta-hackathon-2026", "html_url": "https://github.com/alonsinhoiu/faro-rayosx-meta-hackathon-2026", "track": "Build for Your World", "domain": "Multimodal Vision & Video (SAM / Vision)", "summary": "Audits rental listings with vision and voice to protect tenants", "readme_summary": "Multimodal forensic auditor for Chilean rentals that combines SAM 3.1 segmentation, voice transcription, and Muse Spark 1.3 reasoning with a TypeScript verification engine and contradiction graph for listing analysis.", "tech_highlights": [ "SAM 3.1 Vision", "Muse Spark 1.3", "Muse Voice Transcribe" ], "created_at": "2026-10-27T14:56:34Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 13, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.8, "score_meta_tooling": 1.8, "score_tech_depth": 1.1, "score_demo": 1.0, "score_total": 5.7, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ] ], "tech": [ [ "Base", "+0.3" ], [ "5+ window commits (13)", "+0.2" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 370, "is_new": false, "commits_delta": 0, "rank_delta": -277, "commits_delta_last_run": 0 }, { "full_name": "Zeeohn/kudilens", "html_url": "https://github.com/Zeeohn/kudilens", "track": "Build for Your World", "domain": "Business, Sales & Commerce", "summary": "Bookkeeping agent that turns market traders photos and voice notes into verified ledgers", "readme_summary": "KudiLens reads sales-book photos and voice notes in 5 Nigerian languages via Telegram/WhatsApp. Uses Muse Spark 1.3 for vision extraction with code verification into hash-chained double-entry ledger. Issues shareable Kudi Passport for lenders.", "tech_highlights": [ "Muse Spark 1.3", "SAM 3.1 Vision", "Telegram + WhatsApp" ], "created_at": "2026-10-30T11:39:55Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 11, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": true, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.8, "score_meta_tooling": 1.8, "score_tech_depth": 1.3, "score_demo": 0.8, "score_total": 5.7, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Eval & benchmark proof", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ] ], "tech": [ [ "Base", "+0.3" ], [ "5+ window commits (11)", "+0.2" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Agent / eval harness", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ] ] }, "rank": 371, "is_new": true, "commits_delta": 11, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "Blackleets/la-asistenta", "html_url": "https://github.com/Blackleets/la-asistenta", "track": "Build for Your World", "domain": "Business, Sales & Commerce", "summary": "AI operator for beauty salons with WhatsApp booking and photo brow analysis.", "readme_summary": "La Asistenta connects discovery, AI brow analysis and real agenda booking via web app and WhatsApp Hermes operator for Ari Vivas Beauty pilot. Owner dashboard manages appointments, waitlist and funnel. Uses Meta AI for chat operation, recommendations and vision analysis.", "tech_highlights": [ "WhatsApp Booking AI", "Vision Brow Analysis", "Salon Dashboard" ], "created_at": "2026-10-27T23:22:58Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 8, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": true, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.8, "score_meta_tooling": 1.8, "score_tech_depth": 1.1, "score_demo": 1.0, "score_total": 5.7, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ], [ "Open-weights / fine-tuning", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "5+ window commits (8)", "+0.2" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 372, "is_new": false, "commits_delta": 2, "rank_delta": -277, "commits_delta_last_run": 0 }, { "full_name": "Fqrina/BenchTruth", "html_url": "https://github.com/Fqrina/BenchTruth", "track": "Push the Frontier", "domain": "Robotics, IoT & Manufacturing", "summary": "Hardware verifier that blocks impossible electronics builds and proves the fix", "readme_summary": "BenchTruth validates DIY electronics builds with a deterministic solver for pins, power and mechanics. It uses Muse Spark 1.3 for intent parsing to project_spec.json, then renderers emit BOM, wiring and firmware gated by compile and simulation.", "tech_highlights": [ "Muse Spark 1.3", "Deterministic Solver", "ESP32 + Arduino" ], "created_at": "2026-10-26T07:13:17Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 3, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": true, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": true, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.6, "score_meta_tooling": 0.8, "score_tech_depth": 1.3, "score_demo": 1.0, "score_total": 5.7, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "High-impact domain", "+0.4" ], [ "Eval & benchmark proof", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Muse Spark integration", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Agent / eval harness", "+0.2" ], [ "Automated CI workflow", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 373, "is_new": false, "commits_delta": 0, "rank_delta": -123, "commits_delta_last_run": 0 }, { "full_name": "damipineda/AdForge-AI", "html_url": "https://github.com/damipineda/AdForge-AI", "track": "Build for Your World", "domain": "Business, Sales & Commerce", "summary": "Turns product photos into reviewable ad campaign drafts and visuals", "readme_summary": "Analyzes product photo to propose creative directions, ad copy, audience ideas, and matching visuals for social placements. Built around Meta Model API with Next.js; prototype requiring human review, no auto-publishing.", "tech_highlights": [ "Meta Model API", "Next.js + pnpm", "GenAI Creatives" ], "created_at": "2026-10-29T15:09:03Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 3, "commits_before_window": 1, "prs_total": 0, "prs_merged": 0, "is_preexisting": true, "has_docker": false, "has_tests": false, "has_src": true, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": true, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.1, "score_meta_tooling": 1.8, "score_tech_depth": 0.8, "score_demo": 1.0, "score_total": 5.7, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Eval & benchmark proof", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ] ], "tech": [ [ "Base", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Agent / eval harness", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 374, "is_new": true, "commits_delta": 3, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "ArifbillahKamil/Mathi-MetaAI-Hackathon", "html_url": "https://github.com/ArifbillahKamil/Mathi-MetaAI-Hackathon", "track": "Push the Frontier", "domain": "Education & Knowledge Systems", "summary": "Math solver that verifies answers by two independent code executions", "readme_summary": "Requires two independent methods as real code with matching results, unit and sanity checks for integrals, roots and physics work. Includes scalar comparator, independence guard, local execution backend and Meta Model API client. Indie Push the Frontier entry.", "tech_highlights": [ "Muse Model API", "Dual-Route Verification", "Python Execution" ], "created_at": "2026-10-28T08:22:30Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 2, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": true, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.3, "score_meta_tooling": 1.3, "score_tech_depth": 1.1, "score_demo": 1.0, "score_total": 5.7, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "Domain alignment", "+0.3" ], [ "Eval & benchmark proof", "+0.3" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Agent / eval harness", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 375, "is_new": false, "commits_delta": 2, "rank_delta": 146, "commits_delta_last_run": 0 }, { "full_name": "gamamou/TerraCouncil-Meta-Hackathon-2026", "html_url": "https://github.com/gamamou/TerraCouncil-Meta-Hackathon-2026", "track": "Build for Your World", "domain": "Healthcare, Civic Tech & Sustainability", "summary": "Evidence-first sustainability debate platform for Africa with FAITH and FSDC data", "readme_summary": "TerraCouncil presents jury demo guide, development ledger and scientific evidence docs for SustainAfrica. Stack is Python src with config, data, tests and UI. Uses Meta AI for multi-perspective debate with provenance and no-claim boundaries.", "tech_highlights": [ "Sustainability AI", "Evidence Ledger", "Python + UI" ], "created_at": "2026-10-26T19:59:35Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 307, "commits_before_window": 0, "prs_total": 1, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.7, "score_meta_tooling": 1.8, "score_tech_depth": 1.5, "score_demo": 0.6, "score_total": 5.6, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "High-impact domain", "+0.4" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (307)", "+0.6" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 376, "is_new": false, "commits_delta": 0, "rank_delta": -301, "commits_delta_last_run": 0 }, { "full_name": "phantom007xy/photo-authenticity-checker", "html_url": "https://github.com/phantom007xy/photo-authenticity-checker", "track": "Build for Your World", "domain": "Multimodal Vision & Video (SAM / Vision)", "summary": "Checks if a photo is real, AI-generated or AI-edited with evidence maps.", "readme_summary": "ImageDETECTIVE classifies photos as real, fully generated or partly edited with calibrated confidence and localization. Uses Python app with DINOv3 backbone for image and face analysis. Planned SAM 3.1 and Muse Spark for region naming and explanations.", "tech_highlights": [ "DINOv3 Detector", "SAM 3.1 Vision", "Muse Spark" ], "created_at": "2026-10-28T01:46:07Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 124, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": true, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": true, "has_eval_benchmarks": false, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": true, "live_urls": [ "https://shilinyan99.github.io/AIDE" ], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.5, "score_meta_tooling": 2.1, "score_tech_depth": 1.2, "score_demo": 0.8, "score_total": 5.6, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ] ], "meta": [ [ "Base", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ], [ "Open-weights / fine-tuning", "+0.5" ], [ "Published HF Hub weights", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (124)", "+0.6" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Live web deployment", "+0.4" ] ] }, "rank": 377, "is_new": false, "commits_delta": 115, "rank_delta": 2, "commits_delta_last_run": 0 }, { "full_name": "phantom007xy/ImageDETECTIVE", "html_url": "https://github.com/phantom007xy/ImageDETECTIVE", "track": "Build for Your World", "domain": "Multimodal Vision & Video (SAM / Vision)", "summary": "Checks if a photo is real, AI-generated or AI-edited with evidence maps.", "readme_summary": "ImageDETECTIVE classifies photos as real, fully generated or partly edited with calibrated confidence and localization. Uses Python app with DINOv3 backbone for image and face analysis. Planned SAM 3.1 and Muse Spark for region naming and explanations.", "tech_highlights": [ "DINOv3 Detector", "SAM 3.1 Vision", "Muse Spark" ], "created_at": "2026-10-28T01:46:07Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 124, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": true, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": true, "has_eval_benchmarks": false, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": true, "live_urls": [ "https://shilinyan99.github.io/AIDE" ], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.5, "score_meta_tooling": 2.1, "score_tech_depth": 1.2, "score_demo": 0.8, "score_total": 5.6, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ] ], "meta": [ [ "Base", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ], [ "Open-weights / fine-tuning", "+0.5" ], [ "Published HF Hub weights", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (124)", "+0.6" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Live web deployment", "+0.4" ] ] }, "rank": 378, "is_new": true, "commits_delta": 124, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "judescripts/emberscan", "html_url": "https://github.com/judescripts/emberscan", "track": "Build for Your World", "domain": "Healthcare, Civic Tech & Sustainability", "summary": "Phone walkaround video to rule-by-rule wildfire defensible-space plan", "readme_summary": "EmberScan tracks hazards across phone video, measures distance from wall and checks California rules with citations. Monorepo with apps/workers and deterministic rules engine. Uses SAM 3.1 for tracking and Muse Spark for fix plan.", "tech_highlights": [ "SAM 3.1 Vision", "Muse Spark", "Rules Engine" ], "created_at": "2026-10-26T16:45:42Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 76, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": false, "has_ci": true, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": true, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.9, "score_meta_tooling": 1.8, "score_tech_depth": 1.1, "score_demo": 0.8, "score_total": 5.6, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "High-impact domain", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ], [ "Open-weights / fine-tuning", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (76)", "+0.6" ], [ "Automated CI workflow", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ] ] }, "rank": 379, "is_new": false, "commits_delta": 2, "rank_delta": -189, "commits_delta_last_run": 0 }, { "full_name": "saad-mansour/solang-vision-qc", "html_url": "https://github.com/saad-mansour/solang-vision-qc", "track": "Build for Your World", "domain": "Robotics, IoT & Manufacturing", "summary": "A camera assistant that spots garment defects for factory inspectors.", "readme_summary": "Phone/tablet mounted over final-QC table auto-captures garments when still, runs SAM 3.1 + Muse Spark inspection pipeline, and overlays suspect defects for inspector confirmation. Built on Cloudflare Worker.", "tech_highlights": [ "SAM 3.1 Vision", "Muse Spark", "Cloudflare Workers" ], "created_at": "2026-10-26T20:11:58Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 64, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": false, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": true, "has_eval_benchmarks": false, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": true, "live_urls": [ "https://solang-vision-qc.saadmansour.workers.dev/station/" ], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.9, "score_meta_tooling": 1.8, "score_tech_depth": 0.9, "score_demo": 1.0, "score_total": 5.6, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "High-impact domain", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ], [ "Open-weights / fine-tuning", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (64)", "+0.6" ] ], "demo": [ [ "Base", "+0.4" ], [ "Live web deployment", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 380, "is_new": false, "commits_delta": 26, "rank_delta": -234, "commits_delta_last_run": 0 }, { "full_name": "meta-hackers/fairbuy", "html_url": "https://github.com/meta-hackers/fairbuy", "track": "Build for Your World", "domain": "Business, Sales & Commerce", "summary": "AI shopping researcher that compares source-backed products and seller offers", "readme_summary": "AI shopping research app where users describe needs, refine preferences and compare products. Built with React, TypeScript/Express, Zod contracts and PostgreSQL. Uses Meta Model API for chat and research with Brave search optional.", "tech_highlights": [ "Meta Model API", "React + Express", "Postgres + Zod" ], "created_at": "2026-10-26T19:28:35Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 51, "commits_before_window": 0, "prs_total": 7, "prs_merged": 2, "is_preexisting": false, "has_docker": true, "has_tests": true, "has_src": true, "has_ci": true, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.9, "score_meta_tooling": 1.0, "score_tech_depth": 1.9, "score_demo": 0.8, "score_total": 5.6, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Docker packaging", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (51)", "+0.6" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Automated CI workflow", "+0.2" ], [ "PR review workflow (2 PRs)", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ] ] }, "rank": 381, "is_new": true, "commits_delta": 51, "rank_delta": 0, "commits_delta_last_run": 12 }, { "full_name": "uzbedeveloper/remont", "html_url": "https://github.com/uzbedeveloper/remont", "track": "Build for Your World", "domain": "Business, Sales & Commerce", "summary": "Films a room to get renovation estimate, visualization and contractors", "readme_summary": "Phone-first app that analyzes room video in Uzbek, Russian and English to produce smeta estimate and finished look. Web stack with samples, lib and deploy, live site with sample room. Uses Meta models for video analysis, pricing and Foreman voice assistant.", "tech_highlights": [ "SAM Vision Analysis", "Muse Spark", "Multilingual Voice AI" ], "created_at": "2026-10-28T05:26:47Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 44, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": true, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.8, "score_meta_tooling": 1.3, "score_tech_depth": 1.5, "score_demo": 1.0, "score_total": 5.6, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (44)", "+0.4" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Automated CI workflow", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 382, "is_new": false, "commits_delta": 21, "rank_delta": -213, "commits_delta_last_run": 0 }, { "full_name": "vovnit/Jig", "html_url": "https://github.com/vovnit/Jig", "track": "Build for Your World", "domain": "Autonomous Agents & Workflow Automation", "summary": "Prompts turn into native iOS and web mini-apps from declarative specs", "readme_summary": "Lets users describe small tools; Muse Spark generates declarative spec for screens, schema and actions. Shared JS runtime renders native components on iOS and web with storage and reminders. Includes core runtime, specs and demos.", "tech_highlights": [ "Muse Spark", "Declarative Spec", "JS Native Runtime" ], "created_at": "2026-10-26T16:50:30Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 42, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.9, "score_meta_tooling": 1.8, "score_tech_depth": 1.3, "score_demo": 0.6, "score_total": 5.6, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "High-impact domain", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (42)", "+0.4" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 383, "is_new": false, "commits_delta": 27, "rank_delta": -349, "commits_delta_last_run": 0 }, { "full_name": "flyboxfly/axle-meta-hackathon-2026", "html_url": "https://github.com/flyboxfly/axle-meta-hackathon-2026", "track": "Build for Your World", "domain": "Business, Sales & Commerce", "summary": "Muse Spark freight assistant with verified carrier rates and explanations", "readme_summary": "Local freight prototype where Muse Spark delegates evaluation to Axle synthetic API over authenticated HTTPS. Combines carrier benchmarks, verified calculations and explainable recommendations with server-side credentials. Python API with Docker remote deployment and fixtures/tests.", "tech_highlights": [ "Muse Spark", "Axle Freight API", "Python + Docker" ], "created_at": "2026-10-26T20:54:37Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 41, "commits_before_window": 0, "prs_total": 14, "prs_merged": 13, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": true, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.1, "score_meta_tooling": 0.8, "score_tech_depth": 1.7, "score_demo": 1.0, "score_total": 5.6, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Eval & benchmark proof", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Muse Spark integration", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (41)", "+0.4" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Agent / eval harness", "+0.2" ], [ "PR review workflow (13 PRs)", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 384, "is_new": false, "commits_delta": 19, "rank_delta": -233, "commits_delta_last_run": 0 }, { "full_name": "AdolfoEscobar/CasasCripto", "html_url": "https://github.com/AdolfoEscobar/CasasCripto", "track": "Build for Your World", "domain": "Finance, Crypto & Web3", "summary": "Real estate marketplace for listings that accept cryptocurrency payments.", "readme_summary": "Next.js 16 marketplace connecting crypto-friendly sellers with global buyers, with Property model, owner dashboard, and admin review. Built on ShipFast boilerplate with NextAuth, MongoDB, and SEO public pages. No explicit Meta AI model usage described in README.", "tech_highlights": [ "Next.js 16 + React 19", "NextAuth + MongoDB", "SEO Marketplace UI" ], "created_at": "2026-01-14T06:39:58Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 37, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": true, "has_docker": false, "has_tests": false, "has_src": true, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.8, "score_meta_tooling": 1.8, "score_tech_depth": 1.0, "score_demo": 1.0, "score_total": 5.6, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (37)", "+0.4" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 385, "is_new": false, "commits_delta": 15, "rank_delta": -235, "commits_delta_last_run": 5 }, { "full_name": "Fatdrfrog/meta-ai-hackathon", "html_url": "https://github.com/Fatdrfrog/meta-ai-hackathon", "track": "Build for Your World", "domain": "Business, Sales & Commerce", "summary": "Film a showroom once to power a WhatsApp AI seller that knows products", "readme_summary": "Shop films showroom, AI seller on WhatsApp answers product questions. Built inside airi.chat pnpm monorepo with apps/packages/docs. Uses Meta vision and chat models for catalog extraction and sales dialogue.", "tech_highlights": [ "Muse Vision", "WhatsApp seller", "pnpm + Next.js" ], "created_at": "2026-10-26T12:11:54Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 33, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": true, "has_ci": true, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.8, "score_meta_tooling": 1.8, "score_tech_depth": 1.2, "score_demo": 0.8, "score_total": 5.6, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (33)", "+0.4" ], [ "Modular src/ architecture", "+0.3" ], [ "Automated CI workflow", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ] ] }, "rank": 386, "is_new": false, "commits_delta": 0, "rank_delta": -269, "commits_delta_last_run": 0 }, { "full_name": "NuviraTechnologies/9phc", "html_url": "https://github.com/NuviraTechnologies/9phc", "track": "Push the Frontier", "domain": "Developer Tooling, Infra & Security", "summary": "Nine-check audit that verifies AI research claims with receipts", "readme_summary": "Post-research audit extracts every checkable claim from drafts and runs nine verification checks to return Verified/Corrected/Held verdicts. Python processor program with staged pipeline and tests. Positions as top-layer truth constraint, not detector or guardrail.", "tech_highlights": [ "Claim Verification", "9-Check Pipeline", "Python Audit Tool" ], "created_at": "2026-10-26T19:30:22Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 23, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.1, "score_meta_tooling": 1.6, "score_tech_depth": 1.3, "score_demo": 0.6, "score_total": 5.6, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "High-impact domain", "+0.4" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (23)", "+0.4" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 387, "is_new": false, "commits_delta": 0, "rank_delta": -238, "commits_delta_last_run": 0 }, { "full_name": "bolouvipf/tessercore", "html_url": "https://github.com/bolouvipf/tessercore", "track": "Push the Frontier", "domain": "Developer Tooling, Infra & Security", "summary": "Tiny kernel that drafts, verifies and caches WASM modules generated by Muse models", "readme_summary": "Runtime that loads verified pure-function modules on demand, drafting missing ones via Meta Muse under strict contract. Multi-model verification, WebAssembly sandbox, signing and cache reuse. Built for agents needing safe runtime codegen.", "tech_highlights": [ "Meta Muse Models", "WASM Sandbox", "Node.js Kernel" ], "created_at": "2026-10-29T02:01:35Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 20, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": true, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": true, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.3, "score_meta_tooling": 1.3, "score_tech_depth": 1.0, "score_demo": 1.0, "score_total": 5.6, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "High-impact domain", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "Open-weights / fine-tuning", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (20)", "+0.4" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 388, "is_new": false, "commits_delta": 9, "rank_delta": -97, "commits_delta_last_run": 0 }, { "full_name": "MNKCrypto/watchmate", "html_url": "https://github.com/MNKCrypto/watchmate", "track": "Build for Your World", "domain": "Multimodal Vision & Video (SAM / Vision)", "summary": "Watches long livestreams and cuts personalized highlight reels delivered via Telegram", "readme_summary": "Agent ingests long videos and livestreams, matches content to user preferences from text or voice notes. Cuts per-subscriber reels, self-checks edits and delivers via Telegram. Uses profiles, ingest, timeline and messaging modules.", "tech_highlights": [ "Video Highlight Agent", "Telegram Delivery", "Voice Profiles" ], "created_at": "2026-10-27T01:48:57Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 16, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": true, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.8, "score_meta_tooling": 1.8, "score_tech_depth": 1.0, "score_demo": 1.0, "score_total": 5.6, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (16)", "+0.4" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 389, "is_new": false, "commits_delta": 15, "rank_delta": 31, "commits_delta_last_run": 0 }, { "full_name": "LuciferEvil1/neural-lab", "html_url": "https://github.com/LuciferEvil1/neural-lab", "track": "Push the Frontier", "domain": "Robotics, IoT & Manufacturing", "summary": "On-device 808-param learning brain living in a 3D terrarium with failure memory", "readme_summary": "Android app runs 24-16-16-8 neural net sensing gravity and prediction error in 3D terrarium. Failures sealed locally as FNV-1a Ghosts with fire-and-forget judging. Uses muse-spark-1.3 via Meta Model API for verdicts and blame.", "tech_highlights": [ "Muse Spark 1.3", "On-device Neural Net", "Android + 3D Terrarium" ], "created_at": "2026-10-29T14:09:14Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 11, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": true, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.6, "score_meta_tooling": 1.3, "score_tech_depth": 1.3, "score_demo": 0.4, "score_total": 5.6, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "High-impact domain", "+0.4" ], [ "Eval & benchmark proof", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "5+ window commits (11)", "+0.2" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Agent / eval harness", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ] ] }, "rank": 390, "is_new": true, "commits_delta": 11, "rank_delta": 0, "commits_delta_last_run": 2 }, { "full_name": "duneon97/evidence-gated-repair", "html_url": "https://github.com/duneon97/evidence-gated-repair", "track": "Push the Frontier", "domain": "Developer Tooling, Infra & Security", "summary": "Python repair agent that proves fixes with frozen tests and evidence", "readme_summary": "Generates regression test before patching, freezes with SHA-256, reproduces failure and validates via subprocess pytest. Blocks test editing as fix. Uses deterministic mock models with real test runs for offline demo.", "tech_highlights": [ "Meta-model repair agent", "SHA-256 frozen tests", "Python + pytest" ], "created_at": "2026-10-27T10:45:00Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 10, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": false, "has_ci": true, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": true, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.3, "score_meta_tooling": 1.3, "score_tech_depth": 1.0, "score_demo": 1.0, "score_total": 5.6, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "High-impact domain", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "Open-weights / fine-tuning", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "5+ window commits (10)", "+0.2" ], [ "Automated test suite", "+0.3" ], [ "Automated CI workflow", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 391, "is_new": false, "commits_delta": 2, "rank_delta": -66, "commits_delta_last_run": 0 }, { "full_name": "NextTyrCreator/100proof", "html_url": "https://github.com/NextTyrCreator/100proof", "track": "Build for Your World", "domain": "Multimodal Vision & Video (SAM / Vision)", "summary": "Turns 100-second walkthrough clips into verifiable home inventory for insurers", "readme_summary": "100proof processes up to 5-min walkthrough clips into rooms, items, counts and replacement pricing with video evidence. Next.js app with packet viewer and verify flow. Uses SAM 3.1, Muse Spark 1.3, Muse Wonder and Muse Image.", "tech_highlights": [ "SAM 3.1 Vision", "Muse Spark 1.3", "Muse Wonder Agents" ], "created_at": "2026-10-26T17:19:59Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 9, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": true, "has_ci": true, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": true, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.5, "score_meta_tooling": 2.3, "score_tech_depth": 1.0, "score_demo": 0.8, "score_total": 5.6, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ], [ "Open-weights / fine-tuning", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "5+ window commits (9)", "+0.2" ], [ "Modular src/ architecture", "+0.3" ], [ "Automated CI workflow", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ] ] }, "rank": 392, "is_new": false, "commits_delta": 5, "rank_delta": -161, "commits_delta_last_run": 0 }, { "full_name": "mary-jeon/realcad", "html_url": "https://github.com/mary-jeon/realcad", "track": "Push the Frontier", "domain": "Robotics, IoT & Manufacturing", "summary": "Voice and text to printable CAD with engineering verification and repair", "readme_summary": "Generates STEP/STL/3MF/DXF/BOM from voice, text or photo using build123d/OpenCascade with local verification of holes, interference and printability. Web frontend plus Python backend. Runtime AI is Meta Muse Spark 1.3 via Meta Model API; CAD and checks run locally.", "tech_highlights": [ "Muse Spark 1.3", "build123d OpenCascade", "STEP/STL/3MF Export" ], "created_at": "2026-10-27T05:46:00Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 8, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 1, "score_impact": 2.3, "score_meta_tooling": 1.6, "score_tech_depth": 1.1, "score_demo": 0.6, "score_total": 5.6, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "High-impact domain", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "5+ window commits (8)", "+0.2" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 393, "is_new": true, "commits_delta": 8, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "tanyageorge/curriculum-auditor", "html_url": "https://github.com/tanyageorge/curriculum-auditor", "track": "Build for Your World", "domain": "Education & Knowledge Systems", "summary": "Parses catalog prerequisites into logic to find missing courses and loops", "readme_summary": "Turns prerequisite text into AND/OR logic in conjunctive normal form to audit defects like dead links and loops. Python codebase with loaders, gold-label splits and Muse Spark parsing, plus evals and tests.", "tech_highlights": [ "Muse Spark", "Python + Pytest", "Catalog Evals" ], "created_at": "2026-10-27T22:37:55Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 4, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": true, "has_eval_benchmarks": true, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.9, "score_meta_tooling": 1.8, "score_tech_depth": 1.1, "score_demo": 0.8, "score_total": 5.6, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Eval & benchmark proof", "+0.3" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "Open-weights / fine-tuning", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Agent / eval harness", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ] ] }, "rank": 394, "is_new": false, "commits_delta": 2, "rank_delta": -85, "commits_delta_last_run": 0 }, { "full_name": "arnoldbaraka/cloudbuild-guardian-meta-hackathon", "html_url": "https://github.com/arnoldbaraka/cloudbuild-guardian-meta-hackathon", "track": "Push the Frontier", "domain": "Developer Tooling, Infra & Security", "summary": "Verifiable AI engineer that investigates synthetic K8s incidents with audit logs", "readme_summary": "Investigates synthetic Kubernetes incidents, gathers evidence, requests operator approval, and verifies simulated remediation. Uses Meta Muse Spark 1.3 with hash-chained audit log; sandboxed, no real K8s or shell access.", "tech_highlights": [ "Muse Spark 1.3", "Synthetic Sandbox", "Hash-chained Audit" ], "created_at": "2026-10-27T07:40:42Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 3, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": true, "has_tests": true, "has_src": false, "has_ci": true, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.5, "score_meta_tooling": 1.3, "score_tech_depth": 0.8, "score_demo": 1.0, "score_total": 5.6, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "High-impact domain", "+0.4" ], [ "Docker packaging", "+0.4" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "Automated test suite", "+0.3" ], [ "Automated CI workflow", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 395, "is_new": false, "commits_delta": 0, "rank_delta": -299, "commits_delta_last_run": 0 }, { "full_name": "aminamos/detector-audit-bench", "html_url": "https://github.com/aminamos/detector-audit-bench", "track": "Push the Frontier", "domain": "Legal & Compliance", "summary": "Audits AI-text detectors on civic and legal writing for false positives", "readme_summary": "Benchmarks AI detectors on legislation, filings, public comments and historical texts to expose false human-as-AI flags. Cloudflare Worker + TypeScript stack with data, migrations and docs. Configurable to run live with API keys.", "tech_highlights": [ "Detector Eval Bench", "Civic-Legal Corpus", "Cloudflare Workers" ], "created_at": "2026-10-27T22:42:20Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 2, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": true, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": true, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": true, "live_urls": [ "https://developers.cloudflare.com/workers/wrangler/" ], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.5, "score_meta_tooling": 1.3, "score_tech_depth": 0.8, "score_demo": 1.0, "score_total": 5.6, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "Domain alignment", "+0.3" ], [ "Eval & benchmark proof", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Agent / eval harness", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Live web deployment", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 396, "is_new": false, "commits_delta": 0, "rank_delta": -191, "commits_delta_last_run": 0 }, { "full_name": "sroy0211/agentic-re-verifier-meta-global-ai-developer-hackathon", "html_url": "https://github.com/sroy0211/agentic-re-verifier-meta-global-ai-developer-hackathon", "track": "Push the Frontier", "domain": "Developer Tooling, Infra & Security", "summary": "Deterministic oracle that verifies agent claims about binaries", "readme_summary": "Puts a deterministic gate between agents and ground truth for stripped x86-64 ELF analysis, returning INCONCLUSIVE when evidence is weak. Python notebooks, Streamlit app, SQL/semantic verifiers. Pattern designed to ground Meta models without LLM-as-judge.", "tech_highlights": [ "Deterministic Oracle", "ELF Binary Analysis", "Streamlit + Python" ], "created_at": "2026-11-01T03:52:33Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 1, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": true, "has_tests": false, "has_src": false, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": true, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 3.0, "score_meta_tooling": 1.1, "score_tech_depth": 0.5, "score_demo": 1.0, "score_total": 5.6, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "High-impact domain", "+0.4" ], [ "Eval & benchmark proof", "+0.3" ], [ "Docker packaging", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "Agent / eval harness", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 397, "is_new": true, "commits_delta": 1, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "hackall360/Secure-Mitigation-System", "html_url": "https://github.com/hackall360/Secure-Mitigation-System", "track": "Push the Frontier", "domain": "Developer Tooling, Infra & Security", "summary": "Autonomous purple-team pipeline that attacks, patches and re-verifies code", "readme_summary": "Uses Meta Muse Spark/Wonder to write security patches and air-gapped Docker to prove they work. FastAPI Python 3.12 service with modules and library. Re-runs attacks to verify mitigation.", "tech_highlights": [ "Muse Spark/Wonder", "FastAPI + Docker", "Purple-Team CI/CD" ], "created_at": "2026-10-27T23:47:08Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 639, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.3, "score_meta_tooling": 1.1, "score_tech_depth": 1.5, "score_demo": 0.6, "score_total": 5.5, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "High-impact domain", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (639)", "+0.6" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 398, "is_new": false, "commits_delta": 465, "rank_delta": -321, "commits_delta_last_run": 0 }, { "full_name": "WahahaYes/necronomicon", "html_url": "https://github.com/WahahaYes/necronomicon", "track": "Push the Frontier", "domain": "Developer Tooling, Infra & Security", "summary": "Pre-commit house rules that teach coding agents repo conventions", "readme_summary": "Organizes pre-commit hooks for progressive disclosure: agents see a rule only when they break it, with why and fix guidance. Rust + Python tool with necro --explain, examples and docs. Alternative to stuffing AGENTS.md.", "tech_highlights": [ "Rust + Python", "Pre-commit Hooks", "Agent Steering" ], "created_at": "2026-10-28T22:11:36Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 115, "commits_before_window": 0, "prs_total": 17, "prs_merged": 17, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": true, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 1, "score_impact": 2.3, "score_meta_tooling": 0.5, "score_tech_depth": 1.9, "score_demo": 0.8, "score_total": 5.5, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "High-impact domain", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (115)", "+0.6" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Automated CI workflow", "+0.2" ], [ "PR review workflow (17 PRs)", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ] ] }, "rank": 399, "is_new": true, "commits_delta": 115, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "dkssudgo112/coevo-meta-hackathon", "html_url": "https://github.com/dkssudgo112/coevo-meta-hackathon", "track": "Build for Your World", "domain": "Education & Knowledge Systems", "summary": "Phone coach that watches your screen and asks one question when you are stuck", "readme_summary": "Caddie observes work from phone while user stays in usual AI tool and nudges only when stuck. Leaves minimal lessons and practice scenes with session replays. Cloudflare Workers app with demo, practice-preview and sample flows.", "tech_highlights": [ "Meta AI Integration", "Vision Coaching", "Cloudflare Workers" ], "created_at": "2026-10-30T07:09:46Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 113, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": true, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": true, "live_urls": [ "https://coevo-caddie.coevo-meta-hackathon.workers.dev/demo", "https://coevo-caddie.coevo-meta-hackathon.workers.dev", "https://coevo-caddie.coevo-meta-hackathon.workers.dev/practice-preview", "https://coevo-caddie.coevo-meta-hackathon.workers.dev/sample" ], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 1, "score_impact": 1.8, "score_meta_tooling": 1.1, "score_tech_depth": 1.2, "score_demo": 1.4, "score_total": 5.5, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (113)", "+0.6" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Live web deployment", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 400, "is_new": true, "commits_delta": 113, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "anshupriyan/enheduanna", "html_url": "https://github.com/anshupriyan/enheduanna", "track": "Build for Your World", "domain": "Gaming, Entertainment & Creative Media", "summary": "Autonomous author agent inspired by the world's first named writer", "readme_summary": "Autonomous agent project named Enheduanna reimagining the ancient author as AI. App-based architecture with config, scripts and memory-vision components. Uses Meta AI models per hackathon setup.", "tech_highlights": [ "Autonomous Agent", "Meta Muse Models", "Creative Writing AI" ], "created_at": "2026-10-27T15:05:58Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 78, "commits_before_window": 34, "prs_total": 0, "prs_merged": 0, "is_preexisting": true, "has_docker": false, "has_tests": false, "has_src": true, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 4, "score_impact": 1.7, "score_meta_tooling": 1.6, "score_tech_depth": 1.2, "score_demo": 1.0, "score_total": 5.5, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "General domain", "+0.2" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (78)", "+0.6" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 401, "is_new": true, "commits_delta": 78, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "Vedhrishi/meta-maps", "html_url": "https://github.com/Vedhrishi/meta-maps", "track": "Build for Your World", "domain": "Healthcare, Civic Tech & Sustainability", "summary": "Crowdsourced road-hazard reporting with hazard-aware rerouting and voice control.", "readme_summary": "Lets drivers report potholes, flooding and accidents by photo or sentence, verifies with vision, then updates nearby maps. Backend ranks safe routes and Guardian agent reroutes mid-drive. Uses Meta vision and language models plus Supabase realtime.", "tech_highlights": [ "Vision Hazard Check", "Guardian Rerouting", "Supabase + Voice" ], "created_at": "2026-10-26T19:54:52Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 44, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": true, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": true, "live_urls": [ "https://vedhrishi.github.io/meta-maps/", "https://vedhrishi.github.io/meta-maps/privacy.html" ], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 1, "score_impact": 1.9, "score_meta_tooling": 1.6, "score_tech_depth": 1.0, "score_demo": 1.0, "score_total": 5.5, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "High-impact domain", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (44)", "+0.4" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Live web deployment", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 402, "is_new": false, "commits_delta": 8, "rank_delta": -286, "commits_delta_last_run": 0 }, { "full_name": "ndipto/house-planner", "html_url": "https://github.com/ndipto/house-planner", "track": "Build for Your World", "domain": "General & Emerging Applications", "summary": "Turns plain-word plot briefs into three checked concept floor plans with dimensions", "readme_summary": "Muse Spark parses client brief into structured room program, sizes and adjacencies. Deterministic Python placer creates three typology layouts with walls, doors, windows and north arrow. Checks livability rules and area budget.", "tech_highlights": [ "Muse Spark JSON", "Python floor planner", "Rule-checked layouts" ], "created_at": "2026-10-28T18:55:22Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 42, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": false, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.7, "score_meta_tooling": 1.8, "score_tech_depth": 1.0, "score_demo": 1.0, "score_total": 5.5, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "General domain", "+0.2" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (42)", "+0.4" ], [ "Automated test suite", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 403, "is_new": false, "commits_delta": 38, "rank_delta": 124, "commits_delta_last_run": 0 }, { "full_name": "barath-jayaraman/not-delivered-in-the-blue-truck", "html_url": "https://github.com/barath-jayaraman/not-delivered-in-the-blue-truck", "track": "Build for Your World", "domain": "Business, Sales & Commerce", "summary": "Compares purchases by price, shipping, returns and warranty together", "readme_summary": "Local Next.js prototype comparing total purchase picture across retailers using sample data only. App Router + TypeScript with plain CSS, no live prices or checkout. Built as hackathon Stage 1 demo with browser-local simulation.", "tech_highlights": [ "Next.js + TypeScript", "App Router", "Local Sample Data" ], "created_at": "2026-10-27T13:20:40Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 41, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": true, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": true, "live_urls": [ "https://not-delivered-in-the-blue-truck.vercel.app" ], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.8, "score_meta_tooling": 1.3, "score_tech_depth": 1.0, "score_demo": 1.4, "score_total": 5.5, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (41)", "+0.4" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Live web deployment", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 404, "is_new": false, "commits_delta": 16, "rank_delta": -257, "commits_delta_last_run": 0 }, { "full_name": "predsymod/memex", "html_url": "https://github.com/predsymod/memex", "track": "Push the Frontier", "domain": "Developer Tooling, Infra & Security", "summary": "Self-hosted shared memory layer for AI agents via MCP server and Supabase", "readme_summary": "Durable context store for preferences, decisions and plans shared across any MCP-compatible agent. Uses self-hosted Supabase backend with HTTP MCP server and incremental sync to avoid re-explaining context.", "tech_highlights": [ "MCP Server", "Supabase", "Claude + Muse" ], "created_at": "2026-10-27T02:01:28Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 34, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": true, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": true, "live_urls": [ "https://predsymod.github.io/memex/" ], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.3, "score_meta_tooling": 0.5, "score_tech_depth": 1.5, "score_demo": 1.2, "score_total": 5.5, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "High-impact domain", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (34)", "+0.4" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Automated CI workflow", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Live web deployment", "+0.4" ] ] }, "rank": 405, "is_new": true, "commits_delta": 34, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "youcefbedrani/meta-ai-developer-cerebralvalley", "html_url": "https://github.com/youcefbedrani/meta-ai-developer-cerebralvalley", "track": "Build for Your World", "domain": "Business, Sales & Commerce", "summary": "Founder platform taking ideas from discovery to validation and launch plan", "readme_summary": "Startum AI SaaS platform with Discover, Research, Validate, Plan flow on shared project data. Uses Validation Autopilot agent, voice interviews and pitches, plus Muse Image + SAM 3.1 brand visuals.", "tech_highlights": [ "Muse Spark Vision", "Muse Image", "Next.js + Drizzle" ], "created_at": "2026-10-27T00:20:41Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 31, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": true, "has_tests": false, "has_src": true, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.2, "score_meta_tooling": 1.3, "score_tech_depth": 1.0, "score_demo": 1.0, "score_total": 5.5, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Docker packaging", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (31)", "+0.4" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 406, "is_new": false, "commits_delta": 20, "rank_delta": -251, "commits_delta_last_run": 1 }, { "full_name": "paulrvach/restaurant-ordering-harness", "html_url": "https://github.com/paulrvach/restaurant-ordering-harness", "track": "Build for Your World", "domain": "Business, Sales & Commerce", "summary": "Turns recipes into priced, source-backed vendor order drafts with eval checks", "readme_summary": "TypeScript baseline that converts recipes to ingredient needs and priced vendor drafts with offline behavioral checks. Stack is Node 22, Mastra, npm with evals and synthetic demo. Uses Meta recipe-extraction eval; frontend, live matching and exports are planned.", "tech_highlights": [ "TypeScript + Mastra", "Eval Harness", "Synthetic Demo" ], "created_at": "2026-11-01T01:12:34Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 28, "commits_before_window": 0, "prs_total": 6, "prs_merged": 6, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": true, "has_ci": true, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": true, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.8, "score_meta_tooling": 1.3, "score_tech_depth": 1.6, "score_demo": 0.8, "score_total": 5.5, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Eval & benchmark proof", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (28)", "+0.4" ], [ "Modular src/ architecture", "+0.3" ], [ "Agent / eval harness", "+0.2" ], [ "Automated CI workflow", "+0.2" ], [ "PR review workflow (6 PRs)", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ] ] }, "rank": 407, "is_new": true, "commits_delta": 28, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "EldonL/CountertopRearrange", "html_url": "https://github.com/EldonL/CountertopRearrange", "track": "Build for Your World", "domain": "Gaming, Entertainment & Creative Media", "summary": "AR app that places objects on countertops via vision model coordinates", "readme_summary": "Unity AR app that screenshots the view and asks muse-spark-1.3 where to place an object. Uses Meta Model API Responses API with file upload, JSON x/y output to drive placement.", "tech_highlights": [ "Muse Spark 1.3", "Unity AR + C#", "Meta Model API" ], "created_at": "2026-10-29T20:33:59Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 26, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": true, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": true, "has_setup_guide": false, "has_video_demo": true, "video_urls": [ "https://www.youtube.com/watch?v=2kUAL-EyHI4" ], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.5, "score_meta_tooling": 1.3, "score_tech_depth": 1.2, "score_demo": 1.5, "score_total": 5.5, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "General domain", "+0.2" ], [ "Eval & benchmark proof", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (26)", "+0.4" ], [ "Modular src/ architecture", "+0.3" ], [ "Agent / eval harness", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Video walkthrough", "+1.1" ] ] }, "rank": 408, "is_new": true, "commits_delta": 26, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "pintu544/realitysync", "html_url": "https://github.com/pintu544/realitysync", "track": "Build for Your World", "domain": "Business, Sales & Commerce", "summary": "Warehouse auditor that counts cartons with vision and reconciles ERP records.", "readme_summary": "SAM 3.1 segments and counts cartons from shelf photo/video, deterministic compare checks against simulated ERP, Muse Spark investigates gaps for human approval. Client/server architecture with spec-driven slices and adversarial QA gates. Uses Meta Model API for vision and reasoning.", "tech_highlights": [ "SAM 3.1 Vision", "Muse Spark 1.3", "ERP Reconciliation" ], "created_at": "2026-10-27T02:35:12Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 23, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": true, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.6, "score_meta_tooling": 1.6, "score_tech_depth": 1.5, "score_demo": 0.8, "score_total": 5.5, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Eval & benchmark proof", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (23)", "+0.4" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Agent / eval harness", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ] ] }, "rank": 409, "is_new": false, "commits_delta": 1, "rank_delta": -216, "commits_delta_last_run": 0 }, { "full_name": "sunny-kavixo/proofcausality-ai", "html_url": "https://github.com/sunny-kavixo/proofcausality-ai", "track": "Push the Frontier", "domain": "Autonomous Agents & Workflow Automation", "summary": "System that verifies visual causality and physical actions with cited evidence", "readme_summary": "Evidence-aware verification system for what happened in video and physical actions. Backend checks causality and missing evidence with Rust-accelerated kernels, frontend and evaluation harness for decision audit.", "tech_highlights": [ "Visual Causality AI", "Rust + Python", "FastAPI + Frontend" ], "created_at": "2026-10-28T13:14:55Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 22, "commits_before_window": 0, "prs_total": 8, "prs_merged": 6, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": true, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.3, "score_meta_tooling": 0.5, "score_tech_depth": 1.7, "score_demo": 1.0, "score_total": 5.5, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "High-impact domain", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (22)", "+0.4" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Automated CI workflow", "+0.2" ], [ "PR review workflow (6 PRs)", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 410, "is_new": false, "commits_delta": 3, "rank_delta": -227, "commits_delta_last_run": 0 }, { "full_name": "Foxcrack/viaguard", "html_url": "https://github.com/Foxcrack/viaguard", "track": "Build for Your World", "domain": "Healthcare, Civic Tech & Sustainability", "summary": "Turns phone photos of streets into geolocated, severity-scored reports for cities.", "readme_summary": "Viaguard converts phone photos of roads and construction sites into inspection reports. Built as TypeScript pnpm monorepo with apps and packages. Uses SAM 3.1 for visual segmentation and Muse Spark for report reasoning.", "tech_highlights": [ "SAM 3.1 Vision", "Muse Spark", "TypeScript + pnpm" ], "created_at": "2026-10-30T03:49:25Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 18, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": true, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 3, "score_impact": 1.9, "score_meta_tooling": 1.6, "score_tech_depth": 1.0, "score_demo": 1.0, "score_total": 5.5, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "High-impact domain", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (18)", "+0.4" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 411, "is_new": true, "commits_delta": 18, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "Harsh-Gohel5/GhostTab", "html_url": "https://github.com/Harsh-Gohel5/GhostTab", "track": "Push the Frontier", "domain": "Developer Tooling, Infra & Security", "summary": "Prepares developer workspaces with task context, code evidence and freshness.", "readme_summary": "Workspace preparation tool that pulls Calendar and Google Docs into task briefs. Implements meeting-brief-v3 grounding pipeline with regression evaluation, Alembic migrations and Python + JS apps.", "tech_highlights": [ "Meeting-Brief v3", "Calendar + Docs API", "Python + Next.js" ], "created_at": "2026-10-26T18:42:06Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 16, "commits_before_window": 0, "prs_total": 16, "prs_merged": 15, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": true, "has_ci": true, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 1, "score_impact": 2.3, "score_meta_tooling": 0.8, "score_tech_depth": 1.4, "score_demo": 1.0, "score_total": 5.5, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "High-impact domain", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Muse Spark integration", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (16)", "+0.4" ], [ "Modular src/ architecture", "+0.3" ], [ "Automated CI workflow", "+0.2" ], [ "PR review workflow (15 PRs)", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 412, "is_new": false, "commits_delta": 8, "rank_delta": -149, "commits_delta_last_run": 1 }, { "full_name": "surfiniaburger/barred-muse", "html_url": "https://github.com/surfiniaburger/barred-muse", "track": "Push the Frontier", "domain": "Developer Tooling, Infra & Security", "summary": "Evidence-gated reviewer that verifies security fixes with proofs", "readme_summary": "Transforms AI security opinions into deterministic evidence decisions using AST extractor and receipt validator. Built on Muse-Glimmer-30B multimodal model. Includes scenarios, fixtures, pytest evaluation harness.", "tech_highlights": [ "Muse-Glimmer-30B", "AST Analysis", "Python + pytest" ], "created_at": "2026-10-30T03:27:09Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 13, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": true, "has_eval_benchmarks": true, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.6, "score_meta_tooling": 1.0, "score_tech_depth": 1.3, "score_demo": 0.6, "score_total": 5.5, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "High-impact domain", "+0.4" ], [ "Eval & benchmark proof", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Open-weights / fine-tuning", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "5+ window commits (13)", "+0.2" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Agent / eval harness", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 413, "is_new": true, "commits_delta": 13, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "kiprotichdominic/ev-failed-session-resolver", "html_url": "https://github.com/kiprotichdominic/ev-failed-session-resolver", "track": "Build for Your World", "domain": "Healthcare, Civic Tech & Sustainability", "summary": "Reconstructs failed EV charges to compute auditable refunds for review", "readme_summary": "Reconstructs failed EV sessions from raw inputs, computes owed refunds with code-only arithmetic, and explains with citations. Model explains without computing money. FastAPI + Next.js with 75 tests.", "tech_highlights": [ "Muse Spark 1.3", "FastAPI + Next.js", "Code-Only Audit" ], "created_at": "2026-10-31T21:13:56Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 10, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": false, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": true, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.2, "score_meta_tooling": 1.3, "score_tech_depth": 1.0, "score_demo": 1.0, "score_total": 5.5, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "High-impact domain", "+0.4" ], [ "Eval & benchmark proof", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "5+ window commits (10)", "+0.2" ], [ "Automated test suite", "+0.3" ], [ "Agent / eval harness", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 414, "is_new": true, "commits_delta": 10, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "zhang-systems/meta-hackathon2026-kg-claim-verifier", "html_url": "https://github.com/zhang-systems/meta-hackathon2026-kg-claim-verifier", "track": "Push the Frontier", "domain": "Developer Tooling, Infra & Security", "summary": "Verifier checking AI claims against Wikidata triples with cited evidence", "readme_summary": "Takes claims, splits into atomic facts, fetches Wikidata triples and verifies with evidence. Uses Muse Spark 1.3 for splitting and first verification, Muse Wonder 1.0 for second review via Meta Model API. Built with Python scripts and tests.", "tech_highlights": [ "Muse Spark 1.3", "Muse Wonder 1.0", "Wikidata KG" ], "created_at": "2026-10-26T23:55:35Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 7, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.8, "score_meta_tooling": 1.8, "score_tech_depth": 1.1, "score_demo": 0.8, "score_total": 5.5, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "High-impact domain", "+0.4" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ] ], "tech": [ [ "Base", "+0.3" ], [ "5+ window commits (7)", "+0.2" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ] ] }, "rank": 415, "is_new": false, "commits_delta": 6, "rank_delta": 62, "commits_delta_last_run": 0 }, { "full_name": "vicentewolde/aval", "html_url": "https://github.com/vicentewolde/aval", "track": "Push the Frontier", "domain": "Developer Tooling, Infra & Security", "summary": "Verified listing registry where agents only get claims backed by video proof", "readme_summary": "Broker walkthrough videos are fact-extracted with provenance, then served via a gated MCP gateway. Built with TypeScript, MCP and Meta Model API using Muse Spark + SAM 3.1 to only state proven facts.", "tech_highlights": [ "Muse Spark 1.3", "SAM 3.1 Vision", "MCP Agent Gateway" ], "created_at": "2026-11-01T18:00:31Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 6, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.0, "score_meta_tooling": 1.6, "score_tech_depth": 1.1, "score_demo": 0.8, "score_total": 5.5, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "High-impact domain", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "5+ window commits (6)", "+0.2" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ] ] }, "rank": 416, "is_new": true, "commits_delta": 6, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "nexusguardus/roadsense", "html_url": "https://github.com/nexusguardus/roadsense", "track": "Build for Your World", "domain": "Legal & Compliance", "summary": "Decides junction priority from a photo checked against Spanish traffic law", "readme_summary": "Analyzes driver-seat photos in Spain to answer who goes first with verbatim Reglamento General de Circulacion citations. Uses Muse Spark 1.3 for structured scene facts and SAM 3.1 for evidence overlays. Marks checked only when rule engine and AI agree.", "tech_highlights": [ "SAM 3.1 Vision", "Muse Spark 1.3", "Rule Engine Check" ], "created_at": "2026-10-27T17:18:46Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 5, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.8, "score_meta_tooling": 1.8, "score_tech_depth": 1.1, "score_demo": 0.8, "score_total": 5.5, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ] ], "tech": [ [ "Base", "+0.3" ], [ "5+ window commits (5)", "+0.2" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ] ] }, "rank": 417, "is_new": false, "commits_delta": 0, "rank_delta": -279, "commits_delta_last_run": 0 }, { "full_name": "Cubiczan/sale-ready", "html_url": "https://github.com/Cubiczan/sale-ready", "track": "Build for Your World", "domain": "Business, Sales & Commerce", "summary": "Scores how sale-ready a trades business is and drafts buyer profile", "readme_summary": "Assesses uploaded P&Ls, contracts and site photos into 0-100 score with six sub-scores, fix list and teaser/CIM-lite Markdown/PDF. Python backend with POST /api/upload and local UI via Make demo. Built for HVAC, plumbing and roofing owners.", "tech_highlights": [ "Document + Photo Scoring", "Python API + UI", "PDF Profile Generator" ], "created_at": "2026-10-26T13:44:38Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 5, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.8, "score_meta_tooling": 1.6, "score_tech_depth": 1.1, "score_demo": 1.0, "score_total": 5.5, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "5+ window commits (5)", "+0.2" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 418, "is_new": false, "commits_delta": 0, "rank_delta": -244, "commits_delta_last_run": 0 }, { "full_name": "todoforai/handsfree", "html_url": "https://github.com/todoforai/handsfree", "track": "Push the Frontier", "domain": "Developer Tooling, Infra & Security", "summary": "Voice-driven agent that controls your real Android phone via ADB taps", "readme_summary": "Computer-use agent driving a real Android phone instead of a sandbox, with push-to-talk and locate commands. Muse Voice Transcribe hears, Muse Spark/Wonder plans, SAM 3.1 grounds UI elements to ADB taps.", "tech_highlights": [ "Muse Spark 1.3", "SAM 3.1 Grounding", "Muse Voice + ADB" ], "created_at": "2026-10-26T16:42:01Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 4, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": true, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": true, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.8, "score_meta_tooling": 2.3, "score_tech_depth": 0.6, "score_demo": 0.8, "score_total": 5.5, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "High-impact domain", "+0.4" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ], [ "Open-weights / fine-tuning", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ] ] }, "rank": 419, "is_new": false, "commits_delta": 0, "rank_delta": -113, "commits_delta_last_run": 0 }, { "full_name": "YakubuYinusaT/Talk-for-Meta", "html_url": "https://github.com/YakubuYinusaT/Talk-for-Meta", "track": "Build for Your World", "domain": "Healthcare, Civic Tech & Sustainability", "summary": "Lets people access healthcare and services through a plain phone call, no app needed.", "readme_summary": "Telephony front-end where callers speak needs and SOFA agent routes to care actions. Dockerized Python stack with mocks, tests and deploy configs. Uses Meta Muse models for understanding, context and institutional coordination.", "tech_highlights": [ "Muse Spark", "SOFA Agent", "Docker + Python" ], "created_at": "2026-10-31T11:46:05Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 4, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": true, "has_tests": true, "has_src": true, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.3, "score_meta_tooling": 1.3, "score_tech_depth": 0.9, "score_demo": 1.0, "score_total": 5.5, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "High-impact domain", "+0.4" ], [ "Docker packaging", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 420, "is_new": true, "commits_delta": 4, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "paul8004-lee/besir_global", "html_url": "https://github.com/paul8004-lee/besir_global", "track": "Build for Your World", "domain": "Autonomous Agents & Workflow Automation", "summary": "iOS planning agent that connects shared content into cross-app plans", "readme_summary": "iOS app that sits between phone apps, reads shared content and builds a plan to hand off. Native Swift with Share Extension and proxy layer. Uses Meta Muse Spark to parse shares and fill time, place, and travel details.", "tech_highlights": [ "Muse Spark", "iOS Swift + ShareExt", "Planning Agent" ], "created_at": "2026-10-26T18:18:31Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 581, "commits_before_window": 0, "prs_total": 47, "prs_merged": 47, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": false, "has_ci": true, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": true, "has_eval_benchmarks": false, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.9, "score_meta_tooling": 1.3, "score_tech_depth": 1.6, "score_demo": 0.6, "score_total": 5.4, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "High-impact domain", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "Open-weights / fine-tuning", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (581)", "+0.6" ], [ "Automated test suite", "+0.3" ], [ "Automated CI workflow", "+0.2" ], [ "PR review workflow (47 PRs)", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 421, "is_new": true, "commits_delta": 581, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "Diego-do-na/Exhibit-A", "html_url": "https://github.com/Diego-do-na/Exhibit-A", "track": "Push the Frontier", "domain": "Developer Tooling, Infra & Security", "summary": "Security engine that reports only vulnerabilities proven by sandbox exploit tests", "readme_summary": "Baseline, suspect, exploit, oracle, fix and verify pipeline in isolated containers with canary oracles. Python package with bench, spikes and action. Uses LLMs for adversary, test writer and fixer roles with stable multi-run verdicts.", "tech_highlights": [ "Exploit Verification", "Sandbox Oracle", "Python Security" ], "created_at": "2026-10-26T14:39:27Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 516, "commits_before_window": 0, "prs_total": 2, "prs_merged": 2, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": true, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.3, "score_meta_tooling": 0.8, "score_tech_depth": 1.7, "score_demo": 0.6, "score_total": 5.4, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "High-impact domain", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (516)", "+0.6" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Automated CI workflow", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 422, "is_new": true, "commits_delta": 516, "rank_delta": 0, "commits_delta_last_run": 18 }, { "full_name": "NDilanka/acan", "html_url": "https://github.com/NDilanka/acan", "track": "Push the Frontier", "domain": "Developer Tooling, Infra & Security", "summary": "Scope contract gate that limits coding agents to approved files before edits.", "readme_summary": "Rust workspace where orders become scope contracts enforced before code writes. Routes foreman planning to Muse Spark and workers to Muse Spark Open via Baseten. Stores receipts and clash checks for verification.", "tech_highlights": [ "Muse Spark", "Muse Spark Open", "Rust Workspaces" ], "created_at": "2026-10-26T16:53:16Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 256, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": false, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": true, "has_eval_benchmarks": false, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 1, "score_impact": 2.1, "score_meta_tooling": 1.8, "score_tech_depth": 0.9, "score_demo": 0.6, "score_total": 5.4, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "High-impact domain", "+0.4" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "Open-weights / fine-tuning", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (256)", "+0.6" ] ], "demo": [ [ "Base", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 423, "is_new": true, "commits_delta": 256, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "mohiddin7/indexreel", "html_url": "https://github.com/mohiddin7/indexreel", "track": "Build for Your World", "domain": "Healthcare, Civic Tech & Sustainability", "summary": "Groups viral video posts by source recording and shows side-by-side match frames", "readme_summary": "Ingests clips or X links, groups them by original recording despite crops, mirrors and re-films, with side-by-side frame evidence and split logging. Parses captions into place/date/event claims for approval and flags claims losing video support.", "tech_highlights": [ "Video Fingerprinting", "Frame Matching", "Claim Extraction" ], "created_at": "2026-10-26T00:58:47Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 214, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": true, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 1, "score_impact": 2.0, "score_meta_tooling": 1.1, "score_tech_depth": 1.7, "score_demo": 0.6, "score_total": 5.4, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "High-impact domain", "+0.4" ], [ "Eval & benchmark proof", "+0.3" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (214)", "+0.6" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Agent / eval harness", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 424, "is_new": false, "commits_delta": 116, "rank_delta": -189, "commits_delta_last_run": 0 }, { "full_name": "mohiddin7/IndexReel", "html_url": "https://github.com/mohiddin7/IndexReel", "track": "Build for Your World", "domain": "Healthcare, Civic Tech & Sustainability", "summary": "Groups viral video posts by source recording and shows side-by-side match frames", "readme_summary": "Ingests clips or X links, groups them by original recording despite crops, mirrors and re-films, with side-by-side frame evidence and split logging. Parses captions into place/date/event claims for approval and flags claims losing video support.", "tech_highlights": [ "Video Fingerprinting", "Frame Matching", "Claim Extraction" ], "created_at": "2026-10-26T00:58:47Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 214, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": true, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 1, "score_impact": 2.0, "score_meta_tooling": 1.1, "score_tech_depth": 1.7, "score_demo": 0.6, "score_total": 5.4, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "High-impact domain", "+0.4" ], [ "Eval & benchmark proof", "+0.3" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (214)", "+0.6" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Agent / eval harness", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 425, "is_new": true, "commits_delta": 214, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "Sahaj1207/mothertongue-books", "html_url": "https://github.com/Sahaj1207/mothertongue-books", "track": "Build for Your World", "domain": "Education & Knowledge Systems", "summary": "Creates illustrated native-language children's books with AI agents", "readme_summary": "Lets parents/teachers generate original picture books natively in Telugu, Kannada, Marathi, Swahili and others. Multi-agent team writes, checks reading level and safety, illustrates and makes words tappable. Stack: frontend, backend, Supabase with human review.", "tech_highlights": [ "AI Agent Team", "Multilingual LLM", "Supabase + Vercel" ], "created_at": "2026-10-27T05:17:35Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 85, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": true, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": true, "live_urls": [ "https://mothertongue-books.vercel.app" ], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.6, "score_meta_tooling": 1.6, "score_tech_depth": 1.2, "score_demo": 1.0, "score_total": 5.4, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (85)", "+0.6" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Live web deployment", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 426, "is_new": false, "commits_delta": 56, "rank_delta": -32, "commits_delta_last_run": 0 }, { "full_name": "ashrafi/MetaMuse", "html_url": "https://github.com/ashrafi/MetaMuse", "track": "Build for Your World", "domain": "Healthcare, Civic Tech & Sustainability", "summary": "Bio-responsive Android companion linking health, calendar and finance into daily guidance", "readme_summary": "Android app built with Jetpack Compose and Health Connect SDK, Gradle/Kotlin. Connects health, calendar, financial outflows and social signals into a living companion. Uses Meta Llama 3.1 for reasoning and Llama Guard 3 for safety alignment.", "tech_highlights": [ "Llama 3.1", "Llama Guard 3", "Health Connect + Compose" ], "created_at": "2026-10-27T18:44:24Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 62, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": true, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.9, "score_meta_tooling": 1.3, "score_tech_depth": 1.2, "score_demo": 1.0, "score_total": 5.4, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "High-impact domain", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (62)", "+0.6" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 427, "is_new": false, "commits_delta": 57, "rank_delta": 2, "commits_delta_last_run": 5 }, { "full_name": "FX-DOVE/opie-ai-movie-studio", "html_url": "https://github.com/FX-DOVE/opie-ai-movie-studio", "track": "Build for Your World", "domain": "Gaming, Entertainment & Creative Media", "summary": "Turns one idea into a full film with script, cast, and voice", "readme_summary": "ReelForge Studio writes screenplays, extracts cast and props, storyboards shots with continuity checks, voices dialogue, and cuts MP4. Brainstorm room and director agents support multiple styles and formats. Uses Muse Wonder, Spark, Image.", "tech_highlights": [ "Muse Wonder", "Muse Spark + Image", "Next.js + Docker" ], "created_at": "2026-10-26T18:23:59Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 46, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": true, "has_tests": false, "has_src": true, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 1, "score_impact": 2.1, "score_meta_tooling": 1.3, "score_tech_depth": 1.0, "score_demo": 1.0, "score_total": 5.4, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "General domain", "+0.2" ], [ "Docker packaging", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (46)", "+0.4" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 428, "is_new": false, "commits_delta": 17, "rank_delta": -188, "commits_delta_last_run": 0 }, { "full_name": "SpencerLiang0114/PulsePilot", "html_url": "https://github.com/SpencerLiang0114/PulsePilot", "track": "Build for Your World", "domain": "Healthcare, Civic Tech & Sustainability", "summary": "Estimates heart rate from webcam and explains result quality", "readme_summary": "Research prototype estimating heart rate from webcam via FacePhys model with live lighting and motion coaching. Muse Spark via LangGraph provides coaching and insights. Sensing runs independently of AI service.", "tech_highlights": [ "Muse Spark", "FacePhys rPPG", "LangGraph + Next.js" ], "created_at": "2026-10-27T03:17:01Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 36, "commits_before_window": 11, "prs_total": 0, "prs_merged": 0, "is_preexisting": true, "has_docker": true, "has_tests": true, "has_src": true, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.3, "score_meta_tooling": 0.8, "score_tech_depth": 1.3, "score_demo": 1.0, "score_total": 5.4, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "High-impact domain", "+0.4" ], [ "Docker packaging", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Muse Spark integration", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (36)", "+0.4" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 429, "is_new": true, "commits_delta": 36, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "MohamedAfrasDev/living-diagram", "html_url": "https://github.com/MohamedAfrasDev/living-diagram", "track": "Build for Your World", "domain": "Developer Tooling, Infra & Security", "summary": "Agent tests backend fixes on a simulator and only reports verified metrics", "readme_summary": "LivingDiagrams investigates backend failures like retries and circuit breakers. Next.js app with deterministic simulator engine and API; agent runs controlled experiments. Uses Muse Spark, blocked claims unless engine-recorded.", "tech_highlights": [ "Muse Spark", "Next.js + simulator", "Deterministic engine" ], "created_at": "2026-10-28T04:04:30Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 33, "commits_before_window": 0, "prs_total": 3, "prs_merged": 3, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": true, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.9, "score_meta_tooling": 1.3, "score_tech_depth": 1.2, "score_demo": 1.0, "score_total": 5.4, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "High-impact domain", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (33)", "+0.4" ], [ "Modular src/ architecture", "+0.3" ], [ "PR review workflow (3 PRs)", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 430, "is_new": true, "commits_delta": 33, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "pauljump/producer", "html_url": "https://github.com/pauljump/producer", "track": "Build for Your World", "domain": "Gaming, Entertainment & Creative Media", "summary": "AI session musicians that arrange and play parts under your song", "readme_summary": "Takes unfinished recordings, has AI musicians listen and generate in-time, in-key parts you keep or reject with plain words. Parked Oct 28 2026 to pivot to social story creator. Built during hackathon for Build for Your World theme with ledger and web UI.", "tech_highlights": [ "AI Music Agents", "Modal + Web UI", "Plain-Language Directing" ], "created_at": "2026-10-27T03:37:14Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 24, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": true, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": true, "has_eval_benchmarks": false, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.5, "score_meta_tooling": 2.3, "score_tech_depth": 1.0, "score_demo": 0.6, "score_total": 5.4, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "General domain", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ], [ "Open-weights / fine-tuning", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (24)", "+0.4" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 431, "is_new": false, "commits_delta": 0, "rank_delta": -206, "commits_delta_last_run": 0 }, { "full_name": "selcuksntrk/risklens", "html_url": "https://github.com/selcuksntrk/risklens", "track": "Build for Your World", "domain": "Healthcare, Civic Tech & Sustainability", "summary": "Phone video survey that finds earthquake hazards and verifies fixes.", "readme_summary": "Converts a room video into a non-structural hazard survey with evidence frames and FEMA-grounded fixes. Includes provenance audit trail with models, prompts, hashes, and before/after verification. Deployed web + backend demo for earthquake cities.", "tech_highlights": [ "Video Hazard Survey", "FEMA Fix Library", "Provenance Audit" ], "created_at": "2026-10-29T12:40:40Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 23, "commits_before_window": 0, "prs_total": 1, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": true, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": true, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": true, "live_urls": [ "https://selcuksntrk--risklens-web.us-east.modal.run" ], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.4, "score_meta_tooling": 1.8, "score_tech_depth": 1.0, "score_demo": 1.2, "score_total": 5.4, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "High-impact domain", "+0.4" ] ], "meta": [ [ "Base", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ], [ "Open-weights / fine-tuning", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (23)", "+0.4" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Live web deployment", "+0.4" ] ] }, "rank": 432, "is_new": true, "commits_delta": 23, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "MHSantonu/spatialshelf", "html_url": "https://github.com/MHSantonu/spatialshelf", "track": "Build for Your World", "domain": "Business, Sales & Commerce", "summary": "Turns 10-second shelf video into orderable WhatsApp shop with auto stock", "readme_summary": "Scan-verifies inventory then accepts typed text, handwritten photo or voice-note orders through pick and stock-decrement loop. Shop app + worker with shared storage. Uses Meta vision and language models for shelf scan and order parsing.", "tech_highlights": [ "Muse Spark Vision", "WhatsApp Orders", "Voice + OCR" ], "created_at": "2026-10-27T06:05:21Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 20, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": true, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": true, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.1, "score_meta_tooling": 1.1, "score_tech_depth": 1.2, "score_demo": 1.0, "score_total": 5.4, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Eval & benchmark proof", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (20)", "+0.4" ], [ "Modular src/ architecture", "+0.3" ], [ "Agent / eval harness", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 433, "is_new": false, "commits_delta": 12, "rank_delta": -53, "commits_delta_last_run": 0 }, { "full_name": "TheKingOfMoney09/Photo-CAD", "html_url": "https://github.com/TheKingOfMoney09/Photo-CAD", "track": "Push the Frontier", "domain": "Robotics, IoT & Manufacturing", "summary": "Converts photos of broken parts into measured editable printable CAD models", "readme_summary": "Takes top/side/front photos on a calibration card through segmentation, deterministic OpenCV measurement and parametric CAD to STL/STEP. Plans SAM 3.1 for segmentation. Python app with partforge package and scripts.", "tech_highlights": [ "SAM 3.1 Vision", "OpenCV Metrology", "Parametric CAD" ], "created_at": "2026-10-25T20:53:12Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 17, "commits_before_window": 1, "prs_total": 0, "prs_merged": 0, "is_preexisting": true, "has_docker": false, "has_tests": false, "has_src": true, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.8, "score_meta_tooling": 1.8, "score_tech_depth": 1.0, "score_demo": 0.8, "score_total": 5.4, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "High-impact domain", "+0.4" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (17)", "+0.4" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ] ] }, "rank": 434, "is_new": false, "commits_delta": 17, "rank_delta": -58, "commits_delta_last_run": 0 }, { "full_name": "quartz246/adflank", "html_url": "https://github.com/quartz246/adflank", "track": "Build for Your World", "domain": "Business, Sales & Commerce", "summary": "Reads your website to profile competitor fans and design Meta, TikTok, Google campaigns", "readme_summary": "Paste a website to find competitors via Qloo taste graph, profile their fans and generate segmented campaigns. Daily run refreshes audiences with cited Qloo calls. Next.js app with Docker, scripts and tests, built for Qloo hackathon.", "tech_highlights": [ "Qloo Taste Graph", "Agentic Campaigns", "Next.js + Docker" ], "created_at": "2026-10-29T14:49:20Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 17, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": true, "has_tests": true, "has_src": true, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": true, "live_urls": [ "https://quartz246.github.io/poachly/" ], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.2, "score_meta_tooling": 0.5, "score_tech_depth": 1.3, "score_demo": 1.4, "score_total": 5.4, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Docker packaging", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (17)", "+0.4" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Live web deployment", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 435, "is_new": true, "commits_delta": 17, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "lbwrong/escucha", "html_url": "https://github.com/lbwrong/escucha", "track": "Build for Your World", "domain": "Voice, Speech & Audio AI", "summary": "Full-duplex face-to-face translator for 17 languages that listens while speaking", "readme_summary": "Live conversation translator defaulting Chinese-Spanish that keeps listening while displaying translations. Uses Soniox for streaming ASR/TTS and Meta Model API muse-spark and muse-voice-transcribe for summaries. Python server with static UI and demo mode.", "tech_highlights": [ "Muse Spark 1.3", "Soniox ASR/TTS", "Full-Duplex Audio" ], "created_at": "2026-10-30T07:23:18Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 17, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": false, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.8, "score_meta_tooling": 1.6, "score_tech_depth": 1.0, "score_demo": 1.0, "score_total": 5.4, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (17)", "+0.4" ], [ "Automated test suite", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 436, "is_new": true, "commits_delta": 17, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "samaranez1/Meta-hackathon-", "html_url": "https://github.com/samaranez1/Meta-hackathon-", "track": "Build for Your World", "domain": "Gaming, Entertainment & Creative Media", "summary": "Godot space shooter with AI wingman, live difficulty director, and coach", "readme_summary": "Vertical shooter with 5 sectors and bosses in Godot 4.7. Uses Muse Spark via Meta Model API for briefings, taunts, AI Director and AI Coach with on-device voiceover, plus Muse Image emblem. Falls back to offline mode.", "tech_highlights": [ "Muse Spark 1.3", "Muse Image", "Godot 4.7 + Python" ], "created_at": "2026-10-29T05:31:06Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 12, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": true, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.7, "score_meta_tooling": 1.6, "score_tech_depth": 1.3, "score_demo": 0.8, "score_total": 5.4, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "General domain", "+0.2" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "5+ window commits (12)", "+0.2" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Automated CI workflow", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ] ] }, "rank": 437, "is_new": false, "commits_delta": 0, "rank_delta": -252, "commits_delta_last_run": 0 }, { "full_name": "omenking/meta-ai-field-notes", "html_url": "https://github.com/omenking/meta-ai-field-notes", "track": "Push the Frontier", "domain": "Developer Tooling, Infra & Security", "summary": "Community field notes plus token cost tracking and API key guard tools", "readme_summary": "Unofficial community field notes documenting Meta AI API experiments and gaps. Includes Cost Center dashboard for token spend and Keyguard for key management. Chrome extension plus CLI tooling around dev.meta.ai usage.", "tech_highlights": [ "Meta API Docs", "Cost Tracking", "Chrome Ext + CLI" ], "created_at": "2026-10-23T13:43:42Z", "is_multi_repo": true, "repo_count": 3, "linked_repos": [ { "full_name": "omenking/meta-ai-field-notes", "commits_in_window": 3, "prs_merged": 0, "prs_total": 0, "has_tests": false, "has_docker": false }, { "full_name": "omenking/meta-costcenter", "commits_in_window": 7, "prs_merged": 0, "prs_total": 0, "has_tests": false, "has_docker": false }, { "full_name": "omenking/meta-keyguard", "commits_in_window": 1, "prs_merged": 0, "prs_total": 0, "has_tests": false, "has_docker": false } ], "commits_in_window": 11, "commits_before_window": 30, "prs_total": 0, "prs_merged": 0, "is_preexisting": true, "has_docker": false, "has_tests": false, "has_src": true, "has_ci": true, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 7, "score_impact": 2.3, "score_meta_tooling": 1.8, "score_tech_depth": 0.7, "score_demo": 0.6, "score_total": 5.4, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "High-impact domain", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ] ], "tech": [ [ "Base", "+0.3" ], [ "5+ window commits (11)", "+0.2" ], [ "Modular src/ architecture", "+0.3" ], [ "Automated CI workflow", "+0.2" ], [ "Pre-Oct 26 commits dominate (30)", "-0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 438, "is_new": true, "commits_delta": 11, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "LouisLanganay/fynex-copilot", "html_url": "https://github.com/LouisLanganay/fynex-copilot", "track": "Build for Your World", "domain": "Finance, Crypto & Web3", "summary": "Explains what changed in stocks with links to exact filing passages", "readme_summary": "Fynex Copilot ingests portfolio CSVs, fetches SEC EDGAR, AMF and ESEF filings, and summarizes results and risks per holding. Built on Startups track with Next.js. Uses Muse Spark via Meta Model API to read documents and generate sourced claims.", "tech_highlights": [ "Muse Spark", "SEC EDGAR API", "Next.js App" ], "created_at": "2026-10-27T16:25:13Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 11, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": true, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.8, "score_meta_tooling": 1.3, "score_tech_depth": 1.3, "score_demo": 1.0, "score_total": 5.4, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "5+ window commits (11)", "+0.2" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Automated CI workflow", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 439, "is_new": false, "commits_delta": 10, "rank_delta": -97, "commits_delta_last_run": 0 }, { "full_name": "josephdeakin/im-at-the-races", "html_url": "https://github.com/josephdeakin/im-at-the-races", "track": "Push the Frontier", "domain": "Developer Tooling, Infra & Security", "summary": "Finds and fixes web race conditions by forcing bad timing and proving patches", "readme_summary": "Local dev tool where Muse Spark agent inspects repo and running app, designs timing experiments holding browser responses, freezes reproducer as regression test, then patches in isolated checkout. Monorepo with pnpm, apps/packages and web timeline UI.", "tech_highlights": [ "Muse Spark 1.3", "Browser Timing Chaos", "pnpm Monorepo" ], "created_at": "2026-10-26T22:22:07Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 10, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": true, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.3, "score_meta_tooling": 1.3, "score_tech_depth": 0.8, "score_demo": 1.0, "score_total": 5.4, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "High-impact domain", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "5+ window commits (10)", "+0.2" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 440, "is_new": false, "commits_delta": 9, "rank_delta": 51, "commits_delta_last_run": 2 }, { "full_name": "rightaboutnothing/handoff-meta-hackathon", "html_url": "https://github.com/rightaboutnothing/handoff-meta-hackathon", "track": "Push the Frontier", "domain": "Developer Tooling, Infra & Security", "summary": "Local-first router where Ollama answers safely or escalates to hosted specialists", "readme_summary": "Handoff routes prompts via local Ollama first-responder with escalation to Muse Spark or Grok, logging latency, tokens, and cost. Node.js 18+ scripts with pairings harness. Uses Llama 3.1 8B locally and muse-spark-1.3 via Meta Model API.", "tech_highlights": [ "Muse Spark 1.3", "Llama 3.1 8B Ollama", "AI Router + Benchmark" ], "created_at": "2026-10-26T20:28:49Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 9, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": true, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": true, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.3, "score_meta_tooling": 1.3, "score_tech_depth": 1.0, "score_demo": 0.8, "score_total": 5.4, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "High-impact domain", "+0.4" ], [ "Eval & benchmark proof", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "5+ window commits (9)", "+0.2" ], [ "Modular src/ architecture", "+0.3" ], [ "Agent / eval harness", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ] ] }, "rank": 441, "is_new": false, "commits_delta": 0, "rank_delta": -246, "commits_delta_last_run": 0 }, { "full_name": "surucuonur/meta-hackathon", "html_url": "https://github.com/surucuonur/meta-hackathon", "track": "Push the Frontier", "domain": "Developer Tooling, Infra & Security", "summary": "Measures MobileMoE-S memory bandwidth on vLLM Metal to raise tokens per second", "readme_summary": "Indie project profiling Meta MobileMoE-S on vLLM on Apple M1 Pro Metal. Plots decode steps against 200GB/s bandwidth and 5.2 TFLOPS compute limits. Baseline shows 12-17% bandwidth use to guide MoE batching fixes.", "tech_highlights": [ "MobileMoE-S", "vLLM on Metal", "Bandwidth Profiling" ], "created_at": "2026-10-28T13:13:42Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 8, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": false, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": true, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.4, "score_meta_tooling": 1.3, "score_tech_depth": 0.7, "score_demo": 1.0, "score_total": 5.4, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "High-impact domain", "+0.4" ], [ "Eval & benchmark proof", "+0.3" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "5+ window commits (8)", "+0.2" ], [ "Agent / eval harness", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 442, "is_new": false, "commits_delta": 5, "rank_delta": -56, "commits_delta_last_run": 0 }, { "full_name": "SahinurDEV/PothChol", "html_url": "https://github.com/SahinurDEV/PothChol", "track": "Build for Your World", "domain": "Healthcare, Civic Tech & Sustainability", "summary": "Bangla sidewalk copilot that segments hazards and drafts ward council reports", "readme_summary": "PothChol lets Dhaka pedestrians photo sidewalks for hazard masks and safe-walking guidance in Bangla/English. Built with Next.js calling Meta Responses API for segmentation and planning. Generates formal DNCC/DSCC ward letters.", "tech_highlights": [ "SAM 3.1 Segmentation", "Muse Spark 1.3", "Muse Voice + Next.js" ], "created_at": "2026-10-31T11:47:49Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 8, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": true, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": true, "live_urls": [ "https://pothchol.vercel.app" ], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.6, "score_meta_tooling": 1.8, "score_tech_depth": 0.8, "score_demo": 1.2, "score_total": 5.4, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "High-impact domain", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ] ], "tech": [ [ "Base", "+0.3" ], [ "5+ window commits (8)", "+0.2" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Live web deployment", "+0.4" ] ] }, "rank": 443, "is_new": true, "commits_delta": 8, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "Hisernberg/meta-ai-hackathon-2026", "html_url": "https://github.com/Hisernberg/meta-ai-hackathon-2026", "track": "Build for Your World", "domain": "Education & Knowledge Systems", "summary": "Offline studio archiving elder low-resource language recordings", "readme_summary": "Bhasha records elders to create searchable archive with diarized transcripts, glossaries and cultural cards. Offline-first Next.js PWA with SQLite local storage running self-hosted Muse Glimmer. Community owns data, opt-in export.", "tech_highlights": [ "Muse Glimmer", "Next.js PWA", "SQLite Offline" ], "created_at": "2026-10-26T17:46:44Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 7, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": true, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": true, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.5, "score_meta_tooling": 2.3, "score_tech_depth": 0.8, "score_demo": 0.8, "score_total": 5.4, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ], [ "Open-weights / fine-tuning", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "5+ window commits (7)", "+0.2" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ] ] }, "rank": 444, "is_new": false, "commits_delta": 2, "rank_delta": -162, "commits_delta_last_run": 0 }, { "full_name": "MuraliKrishnaGR/retrodict", "html_url": "https://github.com/MuraliKrishnaGR/retrodict", "track": "Push the Frontier", "domain": "Multimodal Vision & Video (SAM / Vision)", "summary": "Reconstructs timeline of events before a photo with evidence and re-rendered scenes", "readme_summary": "Perceives objects with Muse Spark Open plus local SAM 3.1 masks, reads traces from crops, reasons backward to evidence-cited timeline. Served via Baseten and local Hugging Face transformers. Uses Muse Spark Open and SAM 3.1.", "tech_highlights": [ "SAM 3.1 Vision", "Muse Spark Open", "Baseten Inference" ], "created_at": "2026-10-27T02:47:07Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 6, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": true, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.7, "score_meta_tooling": 1.8, "score_tech_depth": 1.1, "score_demo": 0.8, "score_total": 5.4, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "Domain alignment", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ], [ "Open-weights / fine-tuning", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "5+ window commits (6)", "+0.2" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ] ] }, "rank": 445, "is_new": false, "commits_delta": 3, "rank_delta": 84, "commits_delta_last_run": 0 }, { "full_name": "Redaelm47/resurrection", "html_url": "https://github.com/Redaelm47/resurrection", "track": "Push the Frontier", "domain": "Developer Tooling, Infra & Security", "summary": "Rebuilds working web apps from a screen-recording video with a fidelity score", "readme_summary": "Reads video of legacy app use into a JSON spec, regenerates modern HTML/CSS/JS and redraws assets. Uses Muse Wonder for spec, Muse Code for rebuild, Muse Image for visuals, with bench and tests.", "tech_highlights": [ "Muse Wonder", "Muse Code", "Muse Image" ], "created_at": "2026-10-27T20:29:49Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 4, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": true, "live_urls": [ "https://redaelm47.github.io/resurrection/bench/" ], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.3, "score_meta_tooling": 1.0, "score_tech_depth": 0.9, "score_demo": 1.2, "score_total": 5.4, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "High-impact domain", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ] ], "tech": [ [ "Base", "+0.3" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Live web deployment", "+0.4" ] ] }, "rank": 446, "is_new": false, "commits_delta": 0, "rank_delta": -117, "commits_delta_last_run": 0 }, { "full_name": "kuederleR/mgah-lane-line-auto-distillation", "html_url": "https://github.com/kuederleR/mgah-lane-line-auto-distillation", "track": "Push the Frontier", "domain": "Multimodal Vision & Video (SAM / Vision)", "summary": "Distills monocular 3D lane splines from SAM teacher to Jetson student", "readme_summary": "Teacher uses SAM 3.1 Video tracking, DINOv3 features and Llama 3.2 Vision audit to auto-label 3D lane splines. A ResNet18/MobileNetV4 student predicts vectorized lanes from one frame and exports to TensorRT FP16 on Jetson Orin Nano.", "tech_highlights": [ "SAM 3.1 Video", "DINOv3 + Llama 3.2", "TensorRT on Jetson" ], "created_at": "2026-10-27T00:14:54Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 3, "commits_before_window": 0, "prs_total": 1, "prs_merged": 1, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": true, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.2, "score_meta_tooling": 1.3, "score_tech_depth": 0.9, "score_demo": 1.0, "score_total": 5.4, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "Domain alignment", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "Open-weights / fine-tuning", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 447, "is_new": true, "commits_delta": 3, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "cande-official/oddly-clear-studio", "html_url": "https://github.com/cande-official/oddly-clear-studio", "track": "Build for Your World", "domain": "Education & Knowledge Systems", "summary": "Turns a question, clip and PDF into an evidence-linked visual explainer", "readme_summary": "Web studio that drafts story with Muse Spark from video and document pages, tracks parts with SAM 3.1, and edits beats into vertical film. Node server plus static frontend, deployed on Vercel.", "tech_highlights": [ "SAM 3.1 Vision", "Muse Spark", "Node + Vercel" ], "created_at": "2026-10-31T15:28:14Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 3, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": true, "live_urls": [ "https://oddly-clear-studio.vercel.app", "https://oddly-clear-studio.vercel.app/demo" ], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.8, "score_meta_tooling": 1.3, "score_tech_depth": 0.9, "score_demo": 1.4, "score_total": 5.4, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ] ], "tech": [ [ "Base", "+0.3" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Live web deployment", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 448, "is_new": true, "commits_delta": 3, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "ThineIsMyStrength/docket", "html_url": "https://github.com/ThineIsMyStrength/docket", "track": "Build for Your World", "domain": "Healthcare, Civic Tech & Sustainability", "summary": "Checks and repairs PDFs for accessibility with human approval", "readme_summary": "Checks PDFs against PDF/UA-1 and WCAG 2.1 AA, re-validates repairs, and queues judgment calls for review. Java/Docker engine with journals and cost tracking. Uses Muse Spark 1.3 for figure descriptions and reading order drafts.", "tech_highlights": [ "Muse Spark 1.3", "PDF/UA + WCAG Check", "Java + Docker" ], "created_at": "2026-11-01T03:23:15Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 1, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": true, "has_tests": false, "has_src": false, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.3, "score_meta_tooling": 1.8, "score_tech_depth": 0.3, "score_demo": 1.0, "score_total": 5.4, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "High-impact domain", "+0.4" ], [ "Docker packaging", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ] ], "tech": [ [ "Base", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 449, "is_new": true, "commits_delta": 1, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "codepilots/meta-styles", "html_url": "https://github.com/codepilots/meta-styles", "track": "Build for Your World", "domain": "Business, Sales & Commerce", "summary": "Chat stylist that catalogs wardrobe photos into validated full-look outfits", "readme_summary": "Instagram-DM-style agent builds persistent wardrobe from shared photos, then proposes full looks validated by a fit-rule engine. Every turn shows catalog updates, validation and buy-next suggestions. Runs via proxy needing only a Meta API key.", "tech_highlights": [ "Muse Spark Chat", "Fit-Rule Engine", "IG-Style Chat UI" ], "created_at": "2026-10-28T09:46:20Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 148, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": true, "has_ci": true, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.8, "score_meta_tooling": 1.1, "score_tech_depth": 1.4, "score_demo": 1.0, "score_total": 5.3, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (148)", "+0.6" ], [ "Modular src/ architecture", "+0.3" ], [ "Automated CI workflow", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 450, "is_new": false, "commits_delta": 101, "rank_delta": -59, "commits_delta_last_run": 0 }, { "full_name": "AhmetGokcimen/tender-copilot", "html_url": "https://github.com/AhmetGokcimen/tender-copilot", "track": "Build for Your World", "domain": "Business, Sales & Commerce", "summary": "Ranks Romanian public tenders by fit and drafts eligibility paperwork", "readme_summary": "Licits watches Romania SEAP/SICAP tenders, matches SMEs by eligibility and prepares offer documents. Stack includes Next.js frontend with backend API and i18n EN/RO. Uses Muse models for tender parsing, fit scoring and draft generation.", "tech_highlights": [ "Muse Models", "Next.js + API", "SEAP Tender Data" ], "created_at": "2026-10-26T17:32:08Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 139, "commits_before_window": 0, "prs_total": 44, "prs_merged": 43, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": true, "has_ci": true, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": true, "live_urls": [ "https://tender-copilot-alpha.vercel.app" ], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.8, "score_meta_tooling": 0.5, "score_tech_depth": 1.6, "score_demo": 1.4, "score_total": 5.3, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (139)", "+0.6" ], [ "Modular src/ architecture", "+0.3" ], [ "Automated CI workflow", "+0.2" ], [ "PR review workflow (43 PRs)", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Live web deployment", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 451, "is_new": false, "commits_delta": 91, "rank_delta": -365, "commits_delta_last_run": 0 }, { "full_name": "firstanswerhq/first-answer-muse", "html_url": "https://github.com/firstanswerhq/first-answer-muse", "track": "Build for Your World", "domain": "Business, Sales & Commerce", "summary": "AI front desk that turns customer texts, photos and voicemails into booked jobs.", "readme_summary": "First Answer Sight lets customers text a photo with a reference object to get measurements and next steps. Built with Node.js relay and web boards for owners, it quotes from business price lists. Uses SAM for segmentation and Muse for measurement and bilingual responses.", "tech_highlights": [ "SAM Vision", "Muse Spark", "Node.js Relay" ], "created_at": "2026-10-28T03:31:07Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 98, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.6, "score_meta_tooling": 1.6, "score_tech_depth": 1.5, "score_demo": 0.6, "score_total": 5.3, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (98)", "+0.6" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 452, "is_new": false, "commits_delta": 67, "rank_delta": -260, "commits_delta_last_run": 0 }, { "full_name": "EvilMetaMonkey/dmc-meta-hackathon", "html_url": "https://github.com/EvilMetaMonkey/dmc-meta-hackathon", "track": "Push the Frontier", "domain": "Developer Tooling, Infra & Security", "summary": "Local file history and restore layer for AI coding agent changes", "readme_summary": "dmc runs beside the editor recording file versions to local .dmc folder for inspect, restore and redo with conflict checks. Built on pre-existing dmc with hackathon recovery work. Requires no model, operates offline locally.", "tech_highlights": [ "Dart CLI", "Local Checkpoints", "Agent Recovery" ], "created_at": "2026-10-26T18:03:58Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 73, "commits_before_window": 16, "prs_total": 11, "prs_merged": 11, "is_preexisting": true, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": true, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.3, "score_meta_tooling": 0.5, "score_tech_depth": 1.9, "score_demo": 0.6, "score_total": 5.3, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "High-impact domain", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (73)", "+0.6" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Automated CI workflow", "+0.2" ], [ "PR review workflow (11 PRs)", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 453, "is_new": false, "commits_delta": 6, "rank_delta": -362, "commits_delta_last_run": 0 }, { "full_name": "zeedher-aisuites/bakery-intelligence", "html_url": "https://github.com/zeedher-aisuites/bakery-intelligence", "track": "Build for Your World", "domain": "Business, Sales & Commerce", "summary": "Turns bakery prep videos into evidence-linked recipe drafts for human review", "readme_summary": "Uploads up to 12-min prep videos, stages and runs Muse Spark 1.3 pipeline with frames, timestamped observations and provenance. FastAPI backend with review workspace for correction and export. Requires human approval.", "tech_highlights": [ "Muse Spark 1.3", "FastAPI Backend", "Evidence Review UI" ], "created_at": "2026-10-26T17:11:26Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 50, "commits_before_window": 0, "prs_total": 3, "prs_merged": 3, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.8, "score_meta_tooling": 0.8, "score_tech_depth": 1.7, "score_demo": 1.0, "score_total": 5.3, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Muse Spark integration", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (50)", "+0.6" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "PR review workflow (3 PRs)", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 454, "is_new": false, "commits_delta": 45, "rank_delta": -1, "commits_delta_last_run": 0 }, { "full_name": "nirup2721/show-me", "html_url": "https://github.com/nirup2721/show-me", "track": "Build for Your World", "domain": "Multimodal Vision & Video (SAM / Vision)", "summary": "Points phone camera at machines to get spoken steps with live part outlines", "readme_summary": "Mobile app that transcribes a spoken question, identifies equipment from camera photo and guides repair step-by-step. Uses Muse Voice Transcribe for speech and Muse Spark for visual grounding with camera verification. Node server plus web client.", "tech_highlights": [ "Muse Voice Transcribe", "Muse Spark Vision", "Phone Camera Overlay" ], "created_at": "2026-10-27T15:24:11Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 30, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": true, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": true, "has_eval_benchmarks": false, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.6, "score_meta_tooling": 2.3, "score_tech_depth": 1.0, "score_demo": 0.4, "score_total": 5.3, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ], [ "Open-weights / fine-tuning", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (30)", "+0.4" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ] ] }, "rank": 455, "is_new": false, "commits_delta": 13, "rank_delta": -271, "commits_delta_last_run": 0 }, { "full_name": "DavidFox998/soph-e-runway", "html_url": "https://github.com/DavidFox998/soph-e-runway", "track": "Push the Frontier", "domain": "Developer Tooling, Infra & Security", "summary": "Verification protocol so agent claims become facts only after measurement", "readme_summary": "Reference implementation of Environment Protocol v0 for commerce. Defines Principal, Mandate, Claims with separate assertion/measurement fields to gate agent actions. Team Pistis Sophia, Push the Frontier track.", "tech_highlights": [ "Agent Verification", "MCP Tools", "Python + Schemas" ], "created_at": "2026-10-26T22:23:52Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 26, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.3, "score_meta_tooling": 1.1, "score_tech_depth": 1.3, "score_demo": 0.6, "score_total": 5.3, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "High-impact domain", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (26)", "+0.4" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 456, "is_new": false, "commits_delta": 7, "rank_delta": -186, "commits_delta_last_run": 0 }, { "full_name": "abelxmendoza/hackathon-day-2-agents-101-legal-agent-workshop", "html_url": "https://github.com/abelxmendoza/hackathon-day-2-agents-101-legal-agent-workshop", "track": "Push the Frontier", "domain": "Legal & Compliance", "summary": "Workshop notes and agentic loop code for a multimodal legal document agent", "readme_summary": "Groups Meta Agents 101/102 Legal Agent Workshop work on fictional Northbridge v Caldera case. Implements agentic loop from agent/ with Muse Code plus session notes. Also includes Fireworks Muse Open Models measurement notes.", "tech_highlights": [ "Muse Code", "Muse Spark", "Agentic Loop" ], "created_at": "2026-10-27T17:55:37Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 20, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": false, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": true, "has_eval_benchmarks": false, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.0, "score_meta_tooling": 2.0, "score_tech_depth": 0.7, "score_demo": 0.6, "score_total": 5.3, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "Domain alignment", "+0.3" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ], [ "Open-weights / fine-tuning", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (20)", "+0.4" ] ], "demo": [ [ "Base", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 457, "is_new": false, "commits_delta": 16, "rank_delta": -73, "commits_delta_last_run": 0 }, { "full_name": "CharlesDiovu/moldenovo-ai", "html_url": "https://github.com/CharlesDiovu/moldenovo-ai", "track": "Push the Frontier", "domain": "Healthcare, Civic Tech & Sustainability", "summary": "Evidence-grounded medicinal chemistry copilot that never writes molecules.", "readme_summary": "MolDeNovo plans and reads with Meta models while RDKit applies and verifies chemistry. SAM 3.1 finds structures, Muse Wonder reads SMILES, Muse Spark 1.3 picks edits. Backend plus frontend with human confirmation gates.", "tech_highlights": [ "SAM 3.1 Vision", "Muse Wonder", "Muse Spark 1.3 + RDKit" ], "created_at": "2026-10-27T17:02:49Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 20, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": true, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.1, "score_meta_tooling": 1.8, "score_tech_depth": 1.0, "score_demo": 0.4, "score_total": 5.3, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "High-impact domain", "+0.4" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (20)", "+0.4" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ] ] }, "rank": 458, "is_new": false, "commits_delta": 16, "rank_delta": -19, "commits_delta_last_run": 0 }, { "full_name": "nudiiir/elixir-orderdesk", "html_url": "https://github.com/nudiiir/elixir-orderdesk", "track": "Build for Your World", "domain": "Business, Sales & Commerce", "summary": "Turns WhatsApp voice, photos and chat into booked ERP orders for distributors.", "readme_summary": "Go service that converts Darja voice notes, handwritten lists and chat into ERP orders. Uses Muse Voice Transcribe for audio, SAM 3.1 + Muse Spark for photo and text parsing, then matches to catalogue and books in Odoo, ERPNext, Dolibarr.", "tech_highlights": [ "Muse Spark", "Muse Voice Transcribe", "SAM 3.1 + Go" ], "created_at": "2026-10-31T12:04:18Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 17, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": false, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.8, "score_meta_tooling": 1.8, "score_tech_depth": 0.7, "score_demo": 1.0, "score_total": 5.3, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (17)", "+0.4" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 459, "is_new": true, "commits_delta": 17, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "fandomgames/crop-scout", "html_url": "https://github.com/fandomgames/crop-scout", "track": "Build for Your World", "domain": "Multimodal Vision & Video (SAM / Vision)", "summary": "Quest 3 grow HUD that scans microgreen trays and tracks health.", "readme_summary": "Crop Scout is a Meta Quest 3 passthrough HUD assistant for microgreens growers. It scans trays with headset cameras using SAM 3.1 segmentation and Muse Spark via Meta Model API. Room and DataStore provide shared tray storage and history.", "tech_highlights": [ "SAM 3.1 Vision", "Muse Spark", "Quest 3 + Android" ], "created_at": "2026-10-27T13:14:55Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 15, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.8, "score_meta_tooling": 1.6, "score_tech_depth": 1.3, "score_demo": 0.6, "score_total": 5.3, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (15)", "+0.4" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 460, "is_new": false, "commits_delta": 5, "rank_delta": -325, "commits_delta_last_run": 0 }, { "full_name": "abuz8studios-ship-it/showfront", "html_url": "https://github.com/abuz8studios-ship-it/showfront", "track": "Build for Your World", "domain": "Business, Sales & Commerce", "summary": "Turns car photos into 360 spin, 3D walkaround, video ad, and listing", "readme_summary": "Autonomous showroom pipeline: intake walk-around photos, SAM 3.1 segments vehicle, Muse Image builds showroom scene, then generates 360 spin, Gaussian-splat, commercial and listing. Built solo with app frontend for enthusiasts and dealerships.", "tech_highlights": [ "SAM 3.1 Vision", "Muse Spark 1.3", "Muse Image" ], "created_at": "2026-10-26T16:26:50Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 12, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": true, "live_urls": [ "https://abuz8ai.com" ], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.3, "score_meta_tooling": 2.1, "score_tech_depth": 1.1, "score_demo": 0.8, "score_total": 5.3, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ], [ "Published HF Hub weights", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "5+ window commits (12)", "+0.2" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Live web deployment", "+0.4" ] ] }, "rank": 461, "is_new": false, "commits_delta": 2, "rank_delta": -187, "commits_delta_last_run": 0 }, { "full_name": "Balu-SG/videolab", "html_url": "https://github.com/Balu-SG/videolab", "track": "Push the Frontier", "domain": "Education & Knowledge Systems", "summary": "Phone physics lab that measures motion from slow-motion video with A4 scale", "readme_summary": "VideoLab films experiments with an A4 sheet for scale, tracks objects, converts pixels to metres, and fits physics models. Frontend and backend deployed on Modal. Uses SAM 3.1 for video tracking and Muse Spark agent for planning and explanation.", "tech_highlights": [ "SAM 3.1 Tracking", "Muse Spark Agent", "Modal + Physics Fit" ], "created_at": "2026-10-27T00:31:48Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 11, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": true, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": true, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": true, "live_urls": [ "https://balmca28--videolab-web.us-east.modal.run" ], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.0, "score_meta_tooling": 1.1, "score_tech_depth": 1.0, "score_demo": 1.2, "score_total": 5.3, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "Domain alignment", "+0.3" ], [ "Eval & benchmark proof", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "5+ window commits (11)", "+0.2" ], [ "Modular src/ architecture", "+0.3" ], [ "Agent / eval harness", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Live web deployment", "+0.4" ] ] }, "rank": 462, "is_new": true, "commits_delta": 11, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "gagashun7/feicai-ai-listing-assistant", "html_url": "https://github.com/gagashun7/feicai-ai-listing-assistant", "track": "Build for Your World", "domain": "Business, Sales & Commerce", "summary": "Turns room photos into priced selling plans before student move-out dates", "readme_summary": "Move-Out Agent identifies sellable items from room photos and outputs structured listings with deadline-aware pricing. Built during hackathon separate from Feicai codebase. Demo at move-out-agent.vercel.app uses Muse models.", "tech_highlights": [ "Muse Vision", "Supabase + Vercel", "JS + eval harness" ], "created_at": "2026-10-26T22:30:59Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 10, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": false, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": true, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": true, "live_urls": [ "https://move-out-agent.vercel.app/", "https://move-out-agent.vercel.app" ], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.3, "score_meta_tooling": 2.3, "score_tech_depth": 0.5, "score_demo": 1.2, "score_total": 5.3, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ], [ "Open-weights / fine-tuning", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "5+ window commits (10)", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Live web deployment", "+0.4" ] ] }, "rank": 463, "is_new": false, "commits_delta": 4, "rank_delta": -136, "commits_delta_last_run": 0 }, { "full_name": "adamspencerbarnett-afk/Muse_Dashboard", "html_url": "https://github.com/adamspencerbarnett-afk/Muse_Dashboard", "track": "Push the Frontier", "domain": "Developer Tooling, Infra & Security", "summary": "Local browser workspace to manage Muse Code chats and approvals", "readme_summary": "Drives installed Muse Code via muse serve and @muse-code/sdk with shared sign-in and history. Provides project folders, action approvals, tool and subagent activity view, and token tracking. Runs locally as Node.js web app.", "tech_highlights": [ "Muse Code SDK", "Node.js + Browser UI", "Token + Policy View" ], "created_at": "2026-10-27T13:25:17Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 6, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 1, "score_impact": 2.3, "score_meta_tooling": 1.3, "score_tech_depth": 1.1, "score_demo": 0.6, "score_total": 5.3, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "High-impact domain", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "5+ window commits (6)", "+0.2" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 464, "is_new": true, "commits_delta": 6, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "roszhan2684/Elsewhere", "html_url": "https://github.com/roszhan2684/Elsewhere", "track": "Build for Your World", "domain": "Gaming, Entertainment & Creative Media", "summary": "Simulates two alternate life futures from one decision to explore and fact-check", "readme_summary": "Next.js + FastAPI monorepo that branches one decision into two talkable simulated futures. Uses Muse Wonder, Spark, Voice and Image with stress-test and verification.", "tech_highlights": [ "Muse Wonder", "Next.js + FastAPI", "Muse Voice + Image" ], "created_at": "2026-10-27T17:39:47Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 4, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": true, "has_tests": true, "has_src": true, "has_ci": true, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.1, "score_meta_tooling": 1.1, "score_tech_depth": 1.1, "score_demo": 1.0, "score_total": 5.3, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "General domain", "+0.2" ], [ "Docker packaging", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Automated CI workflow", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 465, "is_new": false, "commits_delta": 0, "rank_delta": -410, "commits_delta_last_run": 0 }, { "full_name": "rankaar/commonground-ai", "html_url": "https://github.com/rankaar/commonground-ai", "track": "Build for Your World", "domain": "Business, Sales & Commerce", "summary": "Property management, fund accounting and governance app for housing associations", "readme_summary": ".NET web app combining unit registry, fund-separated accounting, work orders and voting. Built for the Meta hackathon to replace spreadsheets and manual compliance checks.", "tech_highlights": [ ".NET Web App", "Fund Accounting", "Property Management" ], "created_at": "2026-10-30T09:18:02Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 4, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": true, "live_urls": [ "https://cerebralvalley.ai/e/meta-ai-developer-hackathon" ], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.6, "score_meta_tooling": 1.8, "score_tech_depth": 0.9, "score_demo": 1.0, "score_total": 5.3, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ] ], "tech": [ [ "Base", "+0.3" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Live web deployment", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 466, "is_new": true, "commits_delta": 4, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "jakub-b29/commonground-ai", "html_url": "https://github.com/jakub-b29/commonground-ai", "track": "Build for Your World", "domain": "Business, Sales & Commerce", "summary": "Property management, fund accounting and governance app for housing associations", "readme_summary": ".NET web app combining unit registry, fund-separated accounting, work orders and voting. Built for the Meta hackathon to replace spreadsheets and manual compliance checks.", "tech_highlights": [ ".NET Web App", "Fund Accounting", "Property Management" ], "created_at": "2026-10-30T09:18:02Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 4, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": true, "live_urls": [ "https://cerebralvalley.ai/e/meta-ai-developer-hackathon" ], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.6, "score_meta_tooling": 1.8, "score_tech_depth": 0.9, "score_demo": 1.0, "score_total": 5.3, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ] ], "tech": [ [ "Base", "+0.3" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Live web deployment", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 467, "is_new": true, "commits_delta": 4, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "hhlorsdemir/tryit-meta", "html_url": "https://github.com/hhlorsdemir/tryit-meta", "track": "Build for Your World", "domain": "Business, Sales & Commerce", "summary": "Virtual try-on that shows any store outfit on your own photo", "readme_summary": "Next.js web and iOS app where users upload one photo and paste product links to render full outfits. Uses Muse Spark 1.3 for page parsing and Muse Image for try-on generation in ~20 seconds.", "tech_highlights": [ "Muse Spark 1.3", "Muse Image", "Next.js + iOS" ], "created_at": "2026-10-31T01:58:04Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 2, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": true, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": true, "video_urls": [ "https://youtu.be/l6mrazkdFDs" ], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.5, "score_meta_tooling": 1.3, "score_tech_depth": 0.6, "score_demo": 1.9, "score_total": 5.3, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ] ], "meta": [ [ "Base", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ] ], "tech": [ [ "Base", "+0.3" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Video walkthrough", "+1.1" ], [ "Reproducible setup guide", "+0.4" ] ] }, "rank": 468, "is_new": true, "commits_delta": 2, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "0101julio/rackham", "html_url": "https://github.com/0101julio/rackham", "track": "Build for Your World", "domain": "Education & Knowledge Systems", "summary": "Desktop ghost that translates English to Spanish and reads aloud", "readme_summary": "Desktop companion where users drop English text, PDF or photo to get Spanish translation, TTS audio, and tutor explanations. Python desktop app with floating mascot and local-first translation. Uses TTS/STT with planned Meta model tutoring loop.", "tech_highlights": [ "Python Desktop App", "Translation + TTS", "Tutor Agent" ], "created_at": "2026-10-31T20:38:11Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 2, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": false, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": true, "video_urls": [ "https://youtu.be/f24bCE9luTI" ], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.5, "score_meta_tooling": 1.3, "score_tech_depth": 0.6, "score_demo": 1.9, "score_total": 5.3, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "Automated test suite", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Video walkthrough", "+1.1" ], [ "Reproducible setup guide", "+0.4" ] ] }, "rank": 469, "is_new": true, "commits_delta": 2, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "AmineYagoub/ittro", "html_url": "https://github.com/AmineYagoub/ittro", "track": "Build for Your World", "domain": "Healthcare, Civic Tech & Sustainability", "summary": "Voice-only Android guide that finds exact products on shelves for blind shoppers", "readme_summary": "Camera-based shopping companion that guides hand by voice and vibration and confirms product in hand. Android app plus relay backend; uses Muse Voice Transcribe for always-on listening and Muse vision models.", "tech_highlights": [ "Muse Voice Transcribe", "Android + Relay", "Vision Confirmation" ], "created_at": "2026-10-27T08:09:06Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 272, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": true, "has_ci": true, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.9, "score_meta_tooling": 1.3, "score_tech_depth": 1.4, "score_demo": 0.6, "score_total": 5.2, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "High-impact domain", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (272)", "+0.6" ], [ "Modular src/ architecture", "+0.3" ], [ "Automated CI workflow", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 470, "is_new": false, "commits_delta": 265, "rank_delta": -271, "commits_delta_last_run": 0 }, { "full_name": "Safa675/meta-hackathon-project", "html_url": "https://github.com/Safa675/meta-hackathon-project", "track": "Build for Your World", "domain": "Education & Knowledge Systems", "summary": "Chrome companion that notices tab drift and nudges focus back on task", "readme_summary": "MV3 extension Tuck with attention engine for relevance, drift budget and triggers. Background service worker logs events and calls LLM nodes for relevance and nudges. Includes local memory recall and on-page overlay with voice.", "tech_highlights": [ "Muse Code Session", "Chrome MV3 Extension", "Attention Engine" ], "created_at": "2026-10-29T12:29:36Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 55, "commits_before_window": 0, "prs_total": 13, "prs_merged": 12, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": true, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.1, "score_meta_tooling": 0.8, "score_tech_depth": 1.9, "score_demo": 0.4, "score_total": 5.2, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Eval & benchmark proof", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Muse Spark integration", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (55)", "+0.6" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Agent / eval harness", "+0.2" ], [ "PR review workflow (12 PRs)", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ] ] }, "rank": 471, "is_new": true, "commits_delta": 55, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "jerovasgo/evidence-workbench", "html_url": "https://github.com/jerovasgo/evidence-workbench", "track": "Build for Your World", "domain": "Education & Knowledge Systems", "summary": "Verifies scientific claims against code-checked verbatim quotes and evidence maps.", "readme_summary": "Helps researchers compare and audit scientific evidence with quote-linked claims, certainty grades and concordance views. Next.js workbench with evals, excluding clinical advice. Uses Muse models to extract, compare and grade evidence.", "tech_highlights": [ "Muse Verification", "Next.js Workbench", "Evals + Audits" ], "created_at": "2026-10-29T14:56:07Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 52, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": true, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": true, "live_urls": [ "https://evidence-workbench-xi.vercel.app" ], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.8, "score_meta_tooling": 0.5, "score_tech_depth": 1.7, "score_demo": 1.2, "score_total": 5.2, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Eval & benchmark proof", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ] ], "meta": [ [ "Base", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (52)", "+0.6" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Agent / eval harness", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Live web deployment", "+0.4" ] ] }, "rank": 472, "is_new": true, "commits_delta": 52, "rank_delta": 0, "commits_delta_last_run": 1 }, { "full_name": "KedarPanchal/Meta-AI-Hackathon", "html_url": "https://github.com/KedarPanchal/Meta-AI-Hackathon", "track": "Push the Frontier", "domain": "Robotics, IoT & Manufacturing", "summary": "Flies a ROS 2 drone with a fly-connectome brain for forest search and reflexes.", "readme_summary": "Simulates Drosophila CNS to convert camera and mic input into velocity with escape, sidestep and pursuit reflexes. Mission layer directs search for a person in forest via MCP server. Uses Muse models in mission planning over ROS 2 worlds.", "tech_highlights": [ "Drosophila Connectome", "ROS 2 + MCP Server", "Reflex Autonomy" ], "created_at": "2026-10-27T01:32:15Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 49, "commits_before_window": 0, "prs_total": 6, "prs_merged": 6, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": true, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 1, "score_impact": 2.1, "score_meta_tooling": 1.3, "score_tech_depth": 1.2, "score_demo": 0.6, "score_total": 5.2, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "High-impact domain", "+0.4" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (49)", "+0.4" ], [ "Modular src/ architecture", "+0.3" ], [ "PR review workflow (6 PRs)", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 473, "is_new": false, "commits_delta": 21, "rank_delta": -78, "commits_delta_last_run": 0 }, { "full_name": "josephbolus/devops-as-a-service", "html_url": "https://github.com/josephbolus/devops-as-a-service", "track": "Push the Frontier", "domain": "Developer Tooling, Infra & Security", "summary": "Multi-agent system turning GitHub issues into tested pull requests", "readme_summary": "Agents checkout code, fix small well-defined issues, run tests, and open PRs, escalating destructive cases. Includes architecture docs, eval scorecard, and repeatability harness. Built with Muse multi-agent orchestration for Indie track.", "tech_highlights": [ "Muse Agents", "GitHub Automation", "Eval Scorecard" ], "created_at": "2026-10-23T04:28:40Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 47, "commits_before_window": 30, "prs_total": 5, "prs_merged": 1, "is_preexisting": true, "has_docker": false, "has_tests": false, "has_src": false, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.3, "score_meta_tooling": 1.6, "score_tech_depth": 0.7, "score_demo": 0.6, "score_total": 5.2, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "High-impact domain", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (47)", "+0.4" ] ], "demo": [ [ "Base", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 474, "is_new": false, "commits_delta": 4, "rank_delta": -329, "commits_delta_last_run": 0 }, { "full_name": "Marwichmisi/NIATOLIP", "html_url": "https://github.com/Marwichmisi/NIATOLIP", "track": "Push the Frontier", "domain": "Robotics, IoT & Manufacturing", "summary": "Agentic tool that turns natural language into verified PCB designs with fab export", "readme_summary": "Web app where users describe a PCB in natural language and an agent designs, verifies and corrects it with live PCB/schematic/3D preview. Built on tscircuit plus Vercel AI SDK with Meta Model API/OpenAI for 2-layer ESP32/RP2040 boards.", "tech_highlights": [ "tscircuit", "Vercel AI SDK", "Meta Model API" ], "created_at": "2026-10-29T02:00:57Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 35, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": true, "has_tests": false, "has_src": true, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 1, "score_impact": 2.4, "score_meta_tooling": 1.0, "score_tech_depth": 1.0, "score_demo": 0.8, "score_total": 5.2, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "High-impact domain", "+0.4" ], [ "Docker packaging", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (35)", "+0.4" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ] ] }, "rank": 475, "is_new": true, "commits_delta": 35, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "RAWCoder123/groundwork-meta-hackathon", "html_url": "https://github.com/RAWCoder123/groundwork-meta-hackathon", "track": "Build for Your World", "domain": "Autonomous Agents & Workflow Automation", "summary": "Autonomous workspace that turns a brief and PDFs into a commercial concept and permit plan", "readme_summary": "Schema is an agentic workspace for architects and contractors starting from brief and PDFs. Agent owns work queue for concept, permit strategy and review-comment response with human approvals. Built with Next.js, Cloudflare, Drizzle DB for Portland office fit-out demo.", "tech_highlights": [ "Autonomous Agent Queue", "Next.js + Cloudflare", "RAG over PDFs" ], "created_at": "2026-10-27T21:38:47Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 29, "commits_before_window": 0, "prs_total": 8, "prs_merged": 6, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 1, "score_impact": 1.9, "score_meta_tooling": 0.8, "score_tech_depth": 1.5, "score_demo": 1.0, "score_total": 5.2, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "High-impact domain", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Muse Spark integration", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (29)", "+0.4" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "PR review workflow (6 PRs)", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 476, "is_new": false, "commits_delta": 25, "rank_delta": -314, "commits_delta_last_run": 0 }, { "full_name": "Durl15/rfp-copilot", "html_url": "https://github.com/Durl15/rfp-copilot", "track": "Build for Your World", "domain": "Business, Sales & Commerce", "summary": "Ingests government solicitations to tag bid decisions and pull daily opportunity shortlists", "readme_summary": "FastAPI service ingesting pasted text, PDF or SAM.gov IDs, tagging bid/no-bid sections and proxying CivicProcureBot shortlist. Uses Muse Spark via Meta Model API with retry and SQLite logging. Includes prompts, scripts and tests.", "tech_highlights": [ "Muse Spark", "FastAPI + SQLite", "SAM.gov Ingestion" ], "created_at": "2026-10-26T20:34:45Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 26, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.6, "score_meta_tooling": 1.3, "score_tech_depth": 1.3, "score_demo": 1.0, "score_total": 5.2, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (26)", "+0.4" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 477, "is_new": false, "commits_delta": 4, "rank_delta": -357, "commits_delta_last_run": 1 }, { "full_name": "Mashrokit-AI/offer-guard", "html_url": "https://github.com/Mashrokit-AI/offer-guard", "track": "Build for Your World", "domain": "Business, Sales & Commerce", "summary": "Adapts approved creatives to all ad sizes with brand template rules", "readme_summary": "MatchPic adapts one creative to 6-8 placements in Protected or Fast mode, preserving product/logo pixels with proof. Uses Spark for layout specs and QA check with retry, live demo in Hebrew studio workflow.", "tech_highlights": [ "Muse Spark QA", "Brand Templates", "TypeScript + Vitest" ], "created_at": "2026-10-29T19:10:25Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 24, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.8, "score_meta_tooling": 1.3, "score_tech_depth": 1.3, "score_demo": 0.8, "score_total": 5.2, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (24)", "+0.4" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ] ] }, "rank": 478, "is_new": true, "commits_delta": 24, "rank_delta": 0, "commits_delta_last_run": 2 }, { "full_name": "arxideon-dotcom/ARHeroes-Spellbook-Demo", "html_url": "https://github.com/arxideon-dotcom/ARHeroes-Spellbook-Demo", "track": "Build for Your World", "domain": "Gaming, Entertainment & Creative Media", "summary": "Interactive AR spellbook with animated ice magic for fantasy strategy game", "readme_summary": "Unity demo of a living grimoire on a wooden table with four ice spells as medallions. Book art and spell animations were generated with Meta Muse models, looping on selection with titles and stats.", "tech_highlights": [ "Muse Image", "Unity 3D", "Windows Build" ], "created_at": "2026-10-28T02:25:10Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 22, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": true, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": false, "has_video_demo": true, "video_urls": [ "https://www.youtube.com/watch?v=AgeCmKbe4a0" ], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.5, "score_meta_tooling": 1.0, "score_tech_depth": 1.0, "score_demo": 1.7, "score_total": 5.2, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "General domain", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (22)", "+0.4" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Video walkthrough", "+1.1" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 479, "is_new": false, "commits_delta": 13, "rank_delta": -79, "commits_delta_last_run": 0 }, { "full_name": "Majki1/BLE-Jarvis", "html_url": "https://github.com/Majki1/BLE-Jarvis", "track": "Build for Your World", "domain": "Autonomous Agents & Workflow Automation", "summary": "BLE presence desk agent that briefs you on arrival by voice", "readme_summary": "iPhone as BLE beacon plus Mac agent in mac and mobile folders. On arrival it briefs calendar, Jira and news by voice; on away it triages and drafts. Built with Meta AI for voice briefing and replies.", "tech_highlights": [ "BLE Presence", "Voice Agent", "Muse Spark" ], "created_at": "2026-10-27T05:40:16Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 21, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": false, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": true, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.4, "score_meta_tooling": 2.3, "score_tech_depth": 0.7, "score_demo": 0.8, "score_total": 5.2, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "High-impact domain", "+0.4" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ], [ "Open-weights / fine-tuning", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (21)", "+0.4" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ] ] }, "rank": 480, "is_new": false, "commits_delta": 0, "rank_delta": -144, "commits_delta_last_run": 0 }, { "full_name": "jiveyTO/school-agent-network", "html_url": "https://github.com/jiveyTO/school-agent-network", "track": "Build for Your World", "domain": "Education & Knowledge Systems", "summary": "Turns scattered school newsletters into verified per-family actions", "readme_summary": "ParentLoop hubs per school/class where School, Parent and Group agents extract and verify facts from newsletters and chats. Private per-family actions without portal credentials. Docker + Node stack with live demo.", "tech_highlights": [ "Muse Spark Agents", "Node.js + Docker", "Fact Verification" ], "created_at": "2026-10-27T19:22:57Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 19, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": true, "has_tests": true, "has_src": false, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.2, "score_meta_tooling": 1.0, "score_tech_depth": 1.0, "score_demo": 1.0, "score_total": 5.2, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Docker packaging", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (19)", "+0.4" ], [ "Automated test suite", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 481, "is_new": false, "commits_delta": 16, "rank_delta": -278, "commits_delta_last_run": 2 }, { "full_name": "roeku/wardens", "html_url": "https://github.com/roeku/wardens", "track": "Build for Your World", "domain": "Gaming, Entertainment & Creative Media", "summary": "Voice-commanded real-time strategy game with LLM captains and enemy.", "readme_summary": "THE WARDENS is a voice-controlled RTS built in Rust with TypeScript tooling. Local Muse Glimmer converts speech plus fog-of-war context into orders. Enemy broodlord runs as LLM agent with persistent commander history.", "tech_highlights": [ "Muse Glimmer Local", "Rust Game Engine", "Voice Command RTS" ], "created_at": "2026-10-28T02:33:57Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 18, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": true, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": true, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.4, "score_meta_tooling": 2.0, "score_tech_depth": 1.0, "score_demo": 0.8, "score_total": 5.2, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "General domain", "+0.2" ], [ "Multi-module scope (>10 files)", "+0.2" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ], [ "Open-weights / fine-tuning", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (18)", "+0.4" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ] ] }, "rank": 482, "is_new": false, "commits_delta": 3, "rank_delta": -144, "commits_delta_last_run": 0 }, { "full_name": "Iussyan/ExitLab", "html_url": "https://github.com/Iussyan/ExitLab", "track": "Build for Your World", "domain": "Healthcare, Civic Tech & Sustainability", "summary": "3D tabletop evacuation simulator for stress-testing building disruptions.", "readme_summary": "ExitLab is a React Three Fiber and Vite app with Express server for evacuation simulation. Renders architectural scenes and runs disruption scenarios. Uses TypeScript, Tailwind and Vitest with AI-assisted stress testing.", "tech_highlights": [ "React Three Fiber", "Express + Vite", "TypeScript + Tailwind" ], "created_at": "2026-10-28T13:30:44Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 18, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": true, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.2, "score_meta_tooling": 0.5, "score_tech_depth": 1.5, "score_demo": 1.0, "score_total": 5.2, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "High-impact domain", "+0.4" ], [ "Eval & benchmark proof", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (18)", "+0.4" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Agent / eval harness", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 483, "is_new": false, "commits_delta": 0, "rank_delta": -268, "commits_delta_last_run": 0 }, { "full_name": "Joarciniegas/paymind-voice-hackathon", "html_url": "https://github.com/Joarciniegas/paymind-voice-hackathon", "track": "Build for Your World", "domain": "Voice, Speech & Audio AI", "summary": "Bilingual AI voice agent that makes compliant collections calls for car dealers", "readme_summary": "Cloudflare Workers app using Twilio ConversationRelay for bilingual collections calls with identity verification. Uses Muse Spark 1.3, Muse Wonder 1.0 and Muse Voice Transcribe 1.0 via Meta Model API. Adds KV, Durable Objects and Stripe test mode.", "tech_highlights": [ "Muse Spark 1.3", "Twilio Voice Relay", "Cloudflare Workers" ], "created_at": "2026-10-27T13:38:55Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 15, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": true, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": true, "live_urls": [ "https://paymind-voice-hackathon.joarciniegas.workers.dev" ], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.6, "score_meta_tooling": 1.6, "score_tech_depth": 1.0, "score_demo": 1.0, "score_total": 5.2, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (15)", "+0.4" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Live web deployment", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 484, "is_new": true, "commits_delta": 15, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "Jamespino20/Saphene", "html_url": "https://github.com/Jamespino20/Saphene", "track": "Push the Frontier", "domain": "Developer Tooling, Infra & Security", "summary": "CI ledger that verifies agent memory claims against code with file-line receipts", "readme_summary": "Turns docs and specs into structured claims, grep-verifies each against repo code, and fails CI on drift. Runs as GitHub Actions and MCP plugin for Copilot, Cursor and others. Uses model extraction with offline heuristic fallback.", "tech_highlights": [ "MCP Agent Plugin", "GitHub Actions CI", "TypeScript + Grep" ], "created_at": "2026-10-31T05:11:45Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 15, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": true, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": true, "live_urls": [ "https://jamespino20.github.io/Saphene/", "https://metahackathon-saphene.vercel.app" ], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.0, "score_meta_tooling": 0.5, "score_tech_depth": 1.5, "score_demo": 1.2, "score_total": 5.2, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "High-impact domain", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ] ], "meta": [ [ "Base", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (15)", "+0.4" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Automated CI workflow", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Live web deployment", "+0.4" ] ] }, "rank": 485, "is_new": true, "commits_delta": 15, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "not-rajharsh/SessionGuard", "html_url": "https://github.com/not-rajharsh/SessionGuard", "track": "Push the Frontier", "domain": "Developer Tooling, Infra & Security", "summary": "Continuous auth layer that binds sessions to browsers to block cookie replay.", "readme_summary": "Risk engine scores every request, binds sessions to originating browser and triggers Passkey step-up on anomaly. Provides plain-English rationale per decision. Includes demo app, attack harness and browser tests.", "tech_highlights": [ "Risk Scoring Engine", "Passkey Step-Up", "Node.js + Redis" ], "created_at": "2026-10-26T17:33:16Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 12, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 1, "score_impact": 2.3, "score_meta_tooling": 0.8, "score_tech_depth": 1.1, "score_demo": 1.0, "score_total": 5.2, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "High-impact domain", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Muse Spark integration", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "5+ window commits (12)", "+0.2" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 486, "is_new": true, "commits_delta": 12, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "AshuMaths1729/elasticshelf", "html_url": "https://github.com/AshuMaths1729/elasticshelf", "track": "Build for Your World", "domain": "Business, Sales & Commerce", "summary": "Dynamic pricing and replenishment engine for grocery electronic shelf labels.", "readme_summary": "Headless pricing intelligence using PyTorch DQN reinforcement learning with Meta Muse Spark 1.3 decisions. FastAPI backend streams price updates over WebSockets to ESLs.", "tech_highlights": [ "Muse Spark 1.3", "PyTorch DQN", "FastAPI + WebSockets" ], "created_at": "2026-10-28T13:59:58Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 8, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": true, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": true, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.9, "score_meta_tooling": 1.3, "score_tech_depth": 1.0, "score_demo": 1.0, "score_total": 5.2, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Eval & benchmark proof", "+0.3" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "5+ window commits (8)", "+0.2" ], [ "Modular src/ architecture", "+0.3" ], [ "Agent / eval harness", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 487, "is_new": false, "commits_delta": 6, "rank_delta": -84, "commits_delta_last_run": 0 }, { "full_name": "surasakphetmanee/mars-rover-edgecheck", "html_url": "https://github.com/surasakphetmanee/mars-rover-edgecheck", "track": "Push the Frontier", "domain": "Robotics, IoT & Manufacturing", "summary": "Onboard per-command rover safety checker validated against PRISM model checker", "readme_summary": "C dependency-free probabilistic checker computes stuck/crash odds over 8 range bands for each drive arc on 10x11 grid. Terrain from AI4Mars Navcam via Meta SAM 2.1 encoder plus linear probe. All outputs validated against PRISM.", "tech_highlights": [ "SAM 2.1 Vision", "C Model Checker", "PRISM Validated" ], "created_at": "2026-11-01T05:41:28Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 8, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": false, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": true, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.6, "score_meta_tooling": 0.8, "score_tech_depth": 1.0, "score_demo": 0.8, "score_total": 5.2, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "High-impact domain", "+0.4" ], [ "Eval & benchmark proof", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "5+ window commits (8)", "+0.2" ], [ "Automated test suite", "+0.3" ], [ "Agent / eval harness", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ] ] }, "rank": 488, "is_new": true, "commits_delta": 8, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "PruthviRajG25/MetaHackathon", "html_url": "https://github.com/PruthviRajG25/MetaHackathon", "track": "Build for Your World", "domain": "Business, Sales & Commerce", "summary": "Autonomous grocery restocking app that predicts household needs", "readme_summary": "RepeatLess AI is a Next.js 16 App Router + TypeScript + Tailwind app with MongoDB Atlas for household restocking intelligence. Uses Muse Spark and SAM 3.1 per badges. Includes scripts and tests for autonomous grocery workflows.", "tech_highlights": [ "Muse Spark", "SAM 3.1 Vision", "Next.js + MongoDB" ], "created_at": "2026-10-30T13:14:27Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 2, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": true, "live_urls": [ "https://meta-one-delta.vercel.app" ], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.8, "score_meta_tooling": 1.1, "score_tech_depth": 0.9, "score_demo": 1.4, "score_total": 5.2, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Live web deployment", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 489, "is_new": true, "commits_delta": 2, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "KyPython/repair-bench", "html_url": "https://github.com/KyPython/repair-bench", "track": "Push the Frontier", "domain": "Developer Tooling, Infra & Security", "summary": "Sealed demo that verifies UI fixes by observed browser behavior", "readme_summary": "Local verification harness for accessibility menu/dialog fixes and sealed game-world cheats, accepting only functional behavior. Static HTML/Python with tests and patches. States no live Meta inference performed; uses mocked API contract only.", "tech_highlights": [ "Behavioral Verification", "A11y Test Harness", "Python + Chromium" ], "created_at": "2026-10-31T22:34:51Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 2, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": true, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.3, "score_meta_tooling": 1.0, "score_tech_depth": 1.1, "score_demo": 0.8, "score_total": 5.2, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "High-impact domain", "+0.4" ], [ "Eval & benchmark proof", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Agent / eval harness", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ] ] }, "rank": 490, "is_new": true, "commits_delta": 2, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "GuillermoSiaira/dora-farm-agent", "html_url": "https://github.com/GuillermoSiaira/dora-farm-agent", "track": "Build for Your World", "domain": "Autonomous Agents & Workflow Automation", "summary": "Argentine farm planner turning season notes into fortnightly LP crop plans", "readme_summary": "Agent on Meta model parses text, voice or cost-sheet photo into scenarios for a linear-programming engine planning hectares, sales, storage and credit with shadow prices. Deterministic verifier checks numbers. Gradio app with evals and observatory.", "tech_highlights": [ "Meta Agent + Tools", "LP Engine + Verifier", "Gradio + Python" ], "created_at": "2026-10-27T03:59:25Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 187, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": true, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": true, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.9, "score_meta_tooling": 0.5, "score_tech_depth": 1.9, "score_demo": 0.8, "score_total": 5.1, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "High-impact domain", "+0.4" ], [ "Eval & benchmark proof", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ] ], "meta": [ [ "Base", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (187)", "+0.6" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Agent / eval harness", "+0.2" ], [ "Automated CI workflow", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ] ] }, "rank": 491, "is_new": false, "commits_delta": 85, "rank_delta": -147, "commits_delta_last_run": 5 }, { "full_name": "danrave1234/oddhound-claude", "html_url": "https://github.com/danrave1234/oddhound-claude", "track": "Push the Frontier", "domain": "Developer Tooling, Infra & Security", "summary": "Autonomous web testing agent that finds bugs you did not write tests for", "readme_summary": "Active exploratory-testing agent for web apps driven by Meta Muse Spark. Uses ownership proof, run contracts, isolated secret-free browser exploration and double replay verification. Outputs fix briefs for coding AI and retests.", "tech_highlights": [ "Muse Spark", "Playwright Browser", "TypeScript + pnpm" ], "created_at": "2026-10-27T04:00:55Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 71, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.0, "score_meta_tooling": 0.8, "score_tech_depth": 1.5, "score_demo": 0.8, "score_total": 5.1, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "High-impact domain", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ] ], "meta": [ [ "Base", "+0.5" ], [ "Muse Spark integration", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (71)", "+0.6" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ] ] }, "rank": 492, "is_new": false, "commits_delta": 0, "rank_delta": -255, "commits_delta_last_run": 0 }, { "full_name": "zeroday31337x/zdx-muse-data-platform", "html_url": "https://github.com/zeroday31337x/zdx-muse-data-platform", "track": "Push the Frontier", "domain": "Developer Tooling, Infra & Security", "summary": "Data platform with lineage tracking and governed synthetic data", "readme_summary": "Vertical slice for CSV/JSON ingest, analysis, capped 30% synthetic augmentation, and gated export with manifest. Next.js + Prisma + PostgreSQL + S3 stack planned with worker leases. Uses Muse models only for analysis and augmentation.", "tech_highlights": [ "Muse Models", "Next.js + Prisma", "PostgreSQL + S3" ], "created_at": "2026-10-27T17:08:13Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 56, "commits_before_window": 0, "prs_total": 1, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": true, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.0, "score_meta_tooling": 1.1, "score_tech_depth": 1.2, "score_demo": 0.8, "score_total": 5.1, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "High-impact domain", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ] ], "meta": [ [ "Base", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (56)", "+0.6" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ] ] }, "rank": 493, "is_new": false, "commits_delta": 8, "rank_delta": -227, "commits_delta_last_run": 0 }, { "full_name": "hanish-8880/zavero", "html_url": "https://github.com/hanish-8880/zavero", "track": "Build for Your World", "domain": "Voice, Speech & Audio AI", "summary": "Voice-guided helper that shows what to click in Telugu, Hindi or English", "readme_summary": "Windows Python companion triggered by hotkey for voice-guided software use. Maps screenshots to click coordinates and shows localized bubble text. Uses Muse Spark, Muse Wonder, Muse Voice Transcribe and SAM 3.1.", "tech_highlights": [ "Muse Spark + Wonder", "SAM 3.1 Vision", "Voice Transcribe" ], "created_at": "2026-10-26T17:49:24Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 55, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.5, "score_meta_tooling": 1.3, "score_tech_depth": 1.5, "score_demo": 0.8, "score_total": 5.1, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ] ], "meta": [ [ "Base", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (55)", "+0.6" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ] ] }, "rank": 494, "is_new": false, "commits_delta": 13, "rank_delta": -226, "commits_delta_last_run": 0 }, { "full_name": "ngweibin050-dev/aether", "html_url": "https://github.com/ngweibin050-dev/aether", "track": "Build for Your World", "domain": "Multimodal Vision & Video (SAM / Vision)", "summary": "Turns old patent drawings into explained 3D assemblies for holography", "readme_summary": "AETHER Lab converts century-old patent drawings into working 3D assemblies with part explanations and hologram legibility scores. Includes physics research toward headset-free holographic desk. Uses Meta models for drawing understanding, 3D reconstruction and explanation.", "tech_highlights": [ "Meta Vision + 3D", "Patent to 3D Assembly", "Holographic Rendering" ], "created_at": "2026-10-25T04:03:47Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 45, "commits_before_window": 3, "prs_total": 0, "prs_merged": 0, "is_preexisting": true, "has_docker": false, "has_tests": true, "has_src": false, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": true, "live_urls": [ "https://aether-lab-delta.vercel.app/" ], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.8, "score_meta_tooling": 1.3, "score_tech_depth": 1.0, "score_demo": 1.0, "score_total": 5.1, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (45)", "+0.4" ], [ "Automated test suite", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Live web deployment", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 495, "is_new": false, "commits_delta": 38, "rank_delta": -89, "commits_delta_last_run": 0 }, { "full_name": "GarrickJ87/reel-studio-beat-mask", "html_url": "https://github.com/GarrickJ87/reel-studio-beat-mask", "track": "Build for Your World", "domain": "Multimodal Vision & Video (SAM / Vision)", "summary": "Beat-synced video effects masked to the person via SAM 3.1.", "readme_summary": "Reel Studio plug-in that segments the subject with SAM 3.1 and applies effects locked to beats. Includes ingest, beat map, renderer and web app with tests. Built with Python server and static web client for vertical video export.", "tech_highlights": [ "SAM 3.1 Vision", "Beat Detection", "Python + Web App" ], "created_at": "2026-10-27T17:40:01Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 40, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.5, "score_meta_tooling": 1.5, "score_tech_depth": 1.3, "score_demo": 0.8, "score_total": 5.1, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (40)", "+0.4" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ] ] }, "rank": 496, "is_new": false, "commits_delta": 12, "rank_delta": -255, "commits_delta_last_run": 0 }, { "full_name": "imhcode/harga-tetangga", "html_url": "https://github.com/imhcode/harga-tetangga", "track": "Build for Your World", "domain": "Business, Sales & Commerce", "summary": "Android app reads grocery receipts to compare store prices and plan cash", "readme_summary": "Android app for Indonesian households that reads receipt photos and remembers prices per store. Answers cash-to-bring and cheapest-store for a list, then compares plan vs receipt. Built solo on Meta Model API with Indonesian PRD and field tests.", "tech_highlights": [ "Meta Model API", "Android + OCR", "Receipt AI" ], "created_at": "2026-10-27T00:38:45Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 39, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": false, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.8, "score_meta_tooling": 1.6, "score_tech_depth": 0.7, "score_demo": 1.0, "score_total": 5.1, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (39)", "+0.4" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 497, "is_new": false, "commits_delta": 39, "rank_delta": 9, "commits_delta_last_run": 0 }, { "full_name": "irull/SablonAI", "html_url": "https://github.com/irull/SablonAI", "track": "Build for Your World", "domain": "Business, Sales & Commerce", "summary": "Indonesian-language studio for T-shirt briefs, mockups, pricing and orders", "readme_summary": "Indonesian DTF screen-printing studio unifying brief, design, mockup, print-area pricing and ordering. Next.js app with local end-to-end demo and connectors for three Meta models. Status notes connectors await owner API key testing.", "tech_highlights": [ "Next.js Studio", "Meta Models Connector", "DTF Pricing Engine" ], "created_at": "2026-10-30T18:51:10Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 37, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.8, "score_meta_tooling": 1.0, "score_tech_depth": 1.3, "score_demo": 1.0, "score_total": 5.1, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (37)", "+0.4" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 498, "is_new": true, "commits_delta": 37, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "AntonNovozhilov-roof/hotelapp-liveops", "html_url": "https://github.com/AntonNovozhilov-roof/hotelapp-liveops", "track": "Build for Your World", "domain": "Business, Sales & Commerce", "summary": "Hotel ops layer turning guest messages and staff photos into routed verified tasks", "readme_summary": "Next.js operations app where guest requests become classified tasks by department, priority and confidence. Mock mode without API key, demo hotel seeding, QR room pages and shared UI components.", "tech_highlights": [ "Next.js + API Routes", "Meta AI Routing", "Voice + Vision Tasks" ], "created_at": "2026-10-28T19:37:26Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 34, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": true, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.8, "score_meta_tooling": 1.3, "score_tech_depth": 1.0, "score_demo": 1.0, "score_total": 5.1, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (34)", "+0.4" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 499, "is_new": false, "commits_delta": 33, "rank_delta": -18, "commits_delta_last_run": 0 }, { "full_name": "abdelrahmene/sawt", "html_url": "https://github.com/abdelrahmene/sawt", "track": "Build for Your World", "domain": "Business, Sales & Commerce", "summary": "Voice-controlled social marketing agent that understands Algerian Darija", "readme_summary": "Accepts voice notes to write ads, generate creatives, launch campaigns, and reply to customers in Algerian Darija. Runs on Node 22.5 with node:sqlite and zero dependencies, uses Meta model API via MODEL_API_KEY with no Meta account required.", "tech_highlights": [ "Voice AI Agent", "Darija NLP", "Node + SQLite" ], "created_at": "2026-10-30T18:19:02Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 32, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": true, "has_ci": false, "meta_api_verified": false, "partner_infra": "Baseten", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.8, "score_meta_tooling": 1.3, "score_tech_depth": 1.0, "score_demo": 1.0, "score_total": 5.1, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "Partner inference infra", "+0.2" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (32)", "+0.4" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 500, "is_new": true, "commits_delta": 32, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "AdamNatad/Papeliz", "html_url": "https://github.com/AdamNatad/Papeliz", "track": "Build for Your World", "domain": "Education & Knowledge Systems", "summary": "Simple fast notes app with website, help docs and live web client", "readme_summary": "Papeliz is a minimal note-taking app with live web client, marketing site and help docs. Monorepo uses pnpm workspaces with app, site and branding packages. No Meta AI model integration is described in README excerpt.", "tech_highlights": [ "pnpm Workspaces", "Web Notes App", "MIT Licensed" ], "created_at": "2026-10-28T20:54:11Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 28, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": true, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": true, "live_urls": [ "https://papeliz.com", "https://lucaong.github.io/minisearch/", "https://workers.cloudflare.com" ], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.8, "score_meta_tooling": 1.3, "score_tech_depth": 1.0, "score_demo": 1.0, "score_total": 5.1, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (28)", "+0.4" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Live web deployment", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 501, "is_new": true, "commits_delta": 28, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "Sriharsan/relayloom", "html_url": "https://github.com/Sriharsan/relayloom", "track": "Push the Frontier", "domain": "Autonomous Agents & Workflow Automation", "summary": "Shared human-AI workroom that redoes only what goal changes touch", "readme_summary": "Parallel AI specialists work on one goal, preserving valid work on goal edits and publishing only after recorded approval. Zero-dependency Python 3.11 local server with browser UI. Meta adapter built and offline-tested, live inference not yet run.", "tech_highlights": [ "Multi-Agent Workroom", "Meta Adapter", "Python Zero-Dep Install" ], "created_at": "2026-10-26T18:36:05Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 24, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": true, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.3, "score_meta_tooling": 0.5, "score_tech_depth": 1.5, "score_demo": 0.8, "score_total": 5.1, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "High-impact domain", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (24)", "+0.4" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Automated CI workflow", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ] ] }, "rank": 502, "is_new": false, "commits_delta": 20, "rank_delta": -210, "commits_delta_last_run": 0 }, { "full_name": "Mashrokit-AI/matchpic", "html_url": "https://github.com/Mashrokit-AI/matchpic", "track": "Build for Your World", "domain": "Gaming, Entertainment & Creative Media", "summary": "Adapts approved ad creatives to all placement sizes with pixel-proof protection.", "readme_summary": "Uploads finished creative, applies brand templates per size in Protected or Fast mode using Meta Spark models. Preserves product, logo and text pixels with proof and QA check. Live demo serves brand-aware resizing.", "tech_highlights": [ "Muse Spark", "Protected Pixel Mode", "Template QA Check" ], "created_at": "2026-10-29T19:10:25Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 24, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.7, "score_meta_tooling": 1.3, "score_tech_depth": 1.3, "score_demo": 0.8, "score_total": 5.1, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "General domain", "+0.2" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (24)", "+0.4" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ] ] }, "rank": 503, "is_new": true, "commits_delta": 24, "rank_delta": 0, "commits_delta_last_run": 2 }, { "full_name": "seoddhh/meta-ai-hackathon", "html_url": "https://github.com/seoddhh/meta-ai-hackathon", "track": "Build for Your World", "domain": "Gaming, Entertainment & Creative Media", "summary": "1v1 strategy game where natural language orders drive multi-agent 3D battles.", "readme_summary": "SIGNAL WAR takes commander strategy text through Spark strategist to role-based Glimmer executors with engine adjudication. Results are illustrated with Muse Image and archived in a match archive. Stack is Python FastAPI backend with web 3D frontend.", "tech_highlights": [ "Muse Spark Agents", "Muse Image", "FastAPI + Web 3D" ], "created_at": "2026-10-26T11:42:13Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 23, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": true, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": true, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.5, "score_meta_tooling": 1.8, "score_tech_depth": 1.0, "score_demo": 0.8, "score_total": 5.1, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "General domain", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ], [ "Open-weights / fine-tuning", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (23)", "+0.4" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ] ] }, "rank": 504, "is_new": false, "commits_delta": 5, "rank_delta": -202, "commits_delta_last_run": 0 }, { "full_name": "Sachiya2000/snapshop", "html_url": "https://github.com/Sachiya2000/snapshop", "track": "Build for Your World", "domain": "Business, Sales & Commerce", "summary": "One phone photo becomes a ready-to-sell online product listing", "readme_summary": "Segments product with SAM 3.1, generates studio photos with Muse Image, writes titles and pricing with Muse Spark. Next.js 16 + TypeScript + Tailwind, Prisma Postgres on Neon. All Meta Model API calls run server-side via OpenAI SDK.", "tech_highlights": [ "SAM 3.1 Vision", "Muse Spark 1.3", "Next.js + Prisma" ], "created_at": "2026-10-30T17:29:02Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 19, "commits_before_window": 0, "prs_total": 2, "prs_merged": 2, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": true, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.5, "score_meta_tooling": 1.8, "score_tech_depth": 1.0, "score_demo": 0.8, "score_total": 5.1, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (19)", "+0.4" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ] ] }, "rank": 505, "is_new": true, "commits_delta": 19, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "Demperor20/naija-ai-team", "html_url": "https://github.com/Demperor20/naija-ai-team", "track": "Build for Your World", "domain": "Business, Sales & Commerce", "summary": "WhatsApp AI business team handling books, pricing, flyers with approval flow", "readme_summary": "Provides small businesses an AI team on WhatsApp for bookkeeping, pricing, flyers and paperwork requiring approval. Web demo at /try mirrors WhatsApp agents and approval flow. Next.js stack with lib, prompts and scripts.", "tech_highlights": [ "WhatsApp Agents", "Muse Spark", "Next.js" ], "created_at": "2026-10-26T20:10:11Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 17, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": true, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": true, "live_urls": [ "https://naija-ai-team.vercel.app" ], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 1, "score_impact": 1.8, "score_meta_tooling": 1.3, "score_tech_depth": 1.0, "score_demo": 1.0, "score_total": 5.1, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (17)", "+0.4" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Live web deployment", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 506, "is_new": false, "commits_delta": 5, "rank_delta": -312, "commits_delta_last_run": 0 }, { "full_name": "thenguyentrong/skill-translator", "html_url": "https://github.com/thenguyentrong/skill-translator", "track": "Push the Frontier", "domain": "Robotics, IoT & Manufacturing", "summary": "Turns one task video into executable skills for any robot", "readme_summary": "Video-to-skill system where SAM 3.1 tracks objects, Muse Spark writes robot-agnostic skill cards, then per-robot translators generate motions validated in simulation. Includes web viewer and robot models.", "tech_highlights": [ "SAM 3.1 Vision", "Muse Spark 1.3", "Sim Validation" ], "created_at": "2026-10-26T16:35:17Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 12, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": true, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 1, "score_impact": 2.1, "score_meta_tooling": 1.6, "score_tech_depth": 0.8, "score_demo": 0.6, "score_total": 5.1, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "High-impact domain", "+0.4" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "5+ window commits (12)", "+0.2" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 507, "is_new": false, "commits_delta": 0, "rank_delta": -353, "commits_delta_last_run": 0 }, { "full_name": "NivairaaWhite/uzhavan-ai-meta", "html_url": "https://github.com/NivairaaWhite/uzhavan-ai-meta", "track": "Build for Your World", "domain": "Healthcare, Civic Tech & Sustainability", "summary": "Offline-first farming assistant for Tamil Nadu smallholders with crop vision", "readme_summary": "Uzhavan.AI is an offline-first agritech platform with Flutter mobile, FastAPI backend, and on-device vision for low-end Android. Provides crop advice for Tamil Nadu farmers. Integrates 5 Meta AI models with edge computer vision and pytest coverage.", "tech_highlights": [ "Edge Vision AI", "FastAPI + Flutter", "Meta AI Models" ], "created_at": "2026-10-26T11:42:37Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 11, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": true, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.9, "score_meta_tooling": 1.8, "score_tech_depth": 0.8, "score_demo": 0.6, "score_total": 5.1, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "High-impact domain", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ] ], "tech": [ [ "Base", "+0.3" ], [ "5+ window commits (11)", "+0.2" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 508, "is_new": true, "commits_delta": 11, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "nightmoose/pipeline-medic", "html_url": "https://github.com/nightmoose/pipeline-medic", "track": "Push the Frontier", "domain": "Developer Tooling, Infra & Security", "summary": "Diagnoses failing dbt/Airflow jobs, verifies fix in sandbox, opens PR", "readme_summary": "Collects Airflow task, dbt SQL, errors and stats, sends to Muse Spark via Meta Model API for diagnosis and diff patch. Verifies with dbt build in sandbox and re-runs DAG before proposing PR.", "tech_highlights": [ "Muse Spark 1.3", "dbt + Airflow", "Sandbox Verify + PR" ], "created_at": "2026-10-31T20:14:26Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 11, "commits_before_window": 0, "prs_total": 5, "prs_merged": 5, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": false, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.0, "score_meta_tooling": 1.3, "score_tech_depth": 1.0, "score_demo": 0.8, "score_total": 5.1, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "High-impact domain", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "5+ window commits (11)", "+0.2" ], [ "Automated test suite", "+0.3" ], [ "PR review workflow (5 PRs)", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ] ] }, "rank": 509, "is_new": true, "commits_delta": 11, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "vivaxweb/zenvia-product-curation", "html_url": "https://github.com/vivaxweb/zenvia-product-curation", "track": "Build for Your World", "domain": "Business, Sales & Commerce", "summary": "Fashion discovery engine classifying Gen Z vibes for product curation", "readme_summary": "Zenvia is a production fashion platform at zenviashopping.in with AI pipeline to personalize discovery. Uses open-weights models and vibe classification with Streamlit demo. Includes tagger, app.py, scripts and storefront integration.", "tech_highlights": [ "Vibe Classifier", "Streamlit Demo", "Python AI Pipeline" ], "created_at": "2026-10-28T10:28:08Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 10, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": true, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": true, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.1, "score_meta_tooling": 0.5, "score_tech_depth": 1.5, "score_demo": 1.0, "score_total": 5.1, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Eval & benchmark proof", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "5+ window commits (10)", "+0.2" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Agent / eval harness", "+0.2" ], [ "Automated CI workflow", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 510, "is_new": false, "commits_delta": 5, "rank_delta": -205, "commits_delta_last_run": 0 }, { "full_name": "arimilgram-create/unboring", "html_url": "https://github.com/arimilgram-create/unboring", "track": "Build for Your World", "domain": "Gaming, Entertainment & Creative Media", "summary": "Browser AI video editor that auto-plans cuts, captions, and motion graphics", "readme_summary": "UnBoring uploads talking-head video and plans full edits rendered by custom JSON-to-frame engine. Monorepo with Python and Node services plus ffmpeg, preview equals export. Uses Meta AI via Meta API for edit planning and transcripts.", "tech_highlights": [ "Meta AI Video Edit", "JSON Edit Engine", "Python + Node + ffmpeg" ], "created_at": "2026-10-26T20:03:55Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 9, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.4, "score_meta_tooling": 1.8, "score_tech_depth": 1.1, "score_demo": 0.8, "score_total": 5.1, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "General domain", "+0.2" ], [ "Multi-module scope (>10 files)", "+0.2" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ] ], "tech": [ [ "Base", "+0.3" ], [ "5+ window commits (9)", "+0.2" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ] ] }, "rank": 511, "is_new": false, "commits_delta": 0, "rank_delta": -324, "commits_delta_last_run": 0 }, { "full_name": "tiempoespacio/GeoPrice", "html_url": "https://github.com/tiempoespacio/GeoPrice", "track": "Build for Your World", "domain": "Business, Sales & Commerce", "summary": "Crowdsourced neighborhood price index turning free-text sightings into map data.", "readme_summary": "Cloudflare Worker app uses Muse Spark via Meta Model API to parse free-text prices into structured geolocated data. Browsing is free, publishing uses MetaMask as off-chain identity gate. Live at geoprice.dapp.cl.", "tech_highlights": [ "Muse Spark", "Cloudflare Worker", "MetaMask Identity" ], "created_at": "2026-11-01T02:23:33Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 8, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": false, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": true, "has_setup_guide": false, "has_video_demo": true, "video_urls": [ "https://www.youtube.com/watch?v=eqKYygr2MWg" ], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 2, "score_impact": 1.6, "score_meta_tooling": 1.3, "score_tech_depth": 0.7, "score_demo": 1.5, "score_total": 5.1, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Eval & benchmark proof", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "5+ window commits (8)", "+0.2" ], [ "Agent / eval harness", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Video walkthrough", "+1.1" ] ] }, "rank": 512, "is_new": true, "commits_delta": 8, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "AndyCG03/handful-recipes", "html_url": "https://github.com/AndyCG03/handful-recipes", "track": "Build for Your World", "domain": "Multimodal Vision & Video (SAM / Vision)", "summary": "Turns family cooking videos into living recipes linked to clips and voice notes", "readme_summary": "Next.js PWA + Python worker + Supabase Postgres. Uses Muse Voice Transcribe for diarization, Muse Spark 1.3 for steps, and SAM 3.1 to track handful measurements in video.", "tech_highlights": [ "SAM 3.1 Vision", "Muse Spark 1.3", "Muse Voice Transcribe" ], "created_at": "2026-10-28T05:38:36Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 4, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": true, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": true, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": true, "live_urls": [ "https://handful-recipes.vercel.app" ], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.8, "score_meta_tooling": 1.3, "score_tech_depth": 0.8, "score_demo": 1.2, "score_total": 5.1, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Eval & benchmark proof", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ] ], "meta": [ [ "Base", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ] ], "tech": [ [ "Base", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Agent / eval harness", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Live web deployment", "+0.4" ] ] }, "rank": 513, "is_new": false, "commits_delta": 0, "rank_delta": -173, "commits_delta_last_run": 0 }, { "full_name": "Kittybri/reversesteps-visual-memory", "html_url": "https://github.com/Kittybri/reversesteps-visual-memory", "track": "Build for Your World", "domain": "Multimodal Vision & Video (SAM / Vision)", "summary": "Visual memory that finds where a loose disassembly part belonged", "readme_summary": "Upload up to 12 disassembly photos, mark parts, then query with loose-part photo to suggest source steps with highlights. Local workspace with camera capture and Meta adapter; recognition not yet evaluated.", "tech_highlights": [ "Meta Adapter", "Visual Memory", "Python + TS" ], "created_at": "2026-10-26T16:52:08Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 3, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": true, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": true, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.1, "score_meta_tooling": 1.1, "score_tech_depth": 1.3, "score_demo": 0.6, "score_total": 5.1, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Eval & benchmark proof", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Agent / eval harness", "+0.2" ], [ "Automated CI workflow", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 514, "is_new": false, "commits_delta": 0, "rank_delta": -265, "commits_delta_last_run": 0 }, { "full_name": "Riaz9543/smart-fit-agent", "html_url": "https://github.com/Riaz9543/smart-fit-agent", "track": "Build for Your World", "domain": "Business, Sales & Commerce", "summary": "Virtual try-on store that measures your photo and visualizes fitted dresses", "readme_summary": "Upload full-body photo to estimate measurements, match 3 dresses from 30-item catalogue, and generate try-on image. Static frontend with server API using Meta API for measure and image generation.", "tech_highlights": [ "Meta Model API", "Vanilla JS + Vercel", "Virtual Try-On" ], "created_at": "2026-10-30T15:36:30Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 3, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": false, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": true, "live_urls": [ "https://smart-fit-agent.vercel.app" ], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.6, "score_meta_tooling": 1.8, "score_tech_depth": 0.3, "score_demo": 1.4, "score_total": 5.1, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ] ], "tech": [ [ "Base", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Live web deployment", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 515, "is_new": true, "commits_delta": 3, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "tejaspatel2255/ScreenGuard-Meta-AI-Hackathon", "html_url": "https://github.com/tejaspatel2255/ScreenGuard-Meta-AI-Hackathon", "track": "Build for Your World", "domain": "Autonomous Agents & Workflow Automation", "summary": "Pixel-only supervisor that watches browser work and warns on wrong steps", "readme_summary": "AI supervisor watches a shared browser tab, tracks progress through a written procedure from pixels alone for legacy ERP/POS. FastAPI backend + frontend with eval harness, built Oct 27-Nov 4 2026. Plans Muse Spark, SAM 3.1, Voice Transcribe.", "tech_highlights": [ "Muse Spark", "SAM 3.1 Vision", "FastAPI + Node" ], "created_at": "2026-10-26T12:58:28Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 2, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": true, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.9, "score_meta_tooling": 1.3, "score_tech_depth": 1.1, "score_demo": 0.8, "score_total": 5.1, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "High-impact domain", "+0.4" ], [ "Eval & benchmark proof", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ] ], "meta": [ [ "Base", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ] ], "tech": [ [ "Base", "+0.3" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Agent / eval harness", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ] ] }, "rank": 516, "is_new": false, "commits_delta": 0, "rank_delta": -294, "commits_delta_last_run": 0 }, { "full_name": "MrChrisFarrell/ConsultReady", "html_url": "https://github.com/MrChrisFarrell/ConsultReady", "track": "Build for Your World", "domain": "Legal & Compliance", "summary": "Builds reviewable consultation briefs reconciling documents and gaps", "readme_summary": "Turns scattered project records into user-reviewed consultation briefs, reconciling claims and tracking changes with new evidence. Uses Meta models via MODEL_API_KEY for live inference. .NET 10 API with Node web UI.", "tech_highlights": [ ".NET 10 API", "Muse Models", "Node Web UI" ], "created_at": "2026-10-27T12:50:29Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 1, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": true, "has_tests": true, "has_src": true, "has_ci": true, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": true, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.2, "score_meta_tooling": 0.8, "score_tech_depth": 1.3, "score_demo": 0.8, "score_total": 5.1, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Eval & benchmark proof", "+0.3" ], [ "Docker packaging", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ] ], "meta": [ [ "Base", "+0.5" ], [ "Muse Spark integration", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Agent / eval harness", "+0.2" ], [ "Automated CI workflow", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ] ] }, "rank": 517, "is_new": false, "commits_delta": 0, "rank_delta": -265, "commits_delta_last_run": 0 }, { "full_name": "williamchongdlinkup/singapore-eol-companion", "html_url": "https://github.com/williamchongdlinkup/singapore-eol-companion", "track": "Build for Your World", "domain": "Healthcare, Civic Tech & Sustainability", "summary": "Multifaith voice companion for end-of-life care in four languages", "readme_summary": "Voice-enabled spiritual companion covering nine traditions in English, Mandarin, Cantonese and Hokkien. Pipeline uses Muse Glimmer, Spark Open, Wonder and Voice Transcribe plus SeamlessM4T v2 with PII and crisis gates.", "tech_highlights": [ "Muse Spark Open", "Muse Voice Transcribe", "SeamlessM4T v2" ], "created_at": "2026-10-26T21:37:16Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 1, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": true, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": true, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.4, "score_meta_tooling": 2.3, "score_tech_depth": 0.6, "score_demo": 0.8, "score_total": 5.1, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "High-impact domain", "+0.4" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ], [ "Open-weights / fine-tuning", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ] ] }, "rank": 518, "is_new": false, "commits_delta": 0, "rank_delta": -206, "commits_delta_last_run": 0 }, { "full_name": "IamAmasai/hazina-agent", "html_url": "https://github.com/IamAmasai/hazina-agent", "track": "Build for Your World", "domain": "Finance, Crypto & Web3", "summary": "Tax agent turning M-Pesa and receipts into Kenya eTIMS-ready books", "readme_summary": "Hazi gathers M-Pesa, bank statements, receipt photos and voice notes, then Muse Spark vision structures them. Deterministic matcher reconciles every shilling and flags unmatched for month-end compliance. Python agent with UI, evals and fixtures.", "tech_highlights": [ "Muse Spark Vision", "eTIMS Reconciliation", "Python Agent" ], "created_at": "2026-10-28T06:35:04Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 82, "commits_before_window": 0, "prs_total": 3, "prs_merged": 2, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": false, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": true, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.8, "score_meta_tooling": 1.3, "score_tech_depth": 1.1, "score_demo": 0.8, "score_total": 5.0, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Eval & benchmark proof", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (82)", "+0.6" ], [ "Agent / eval harness", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ] ] }, "rank": 519, "is_new": false, "commits_delta": 0, "rank_delta": -265, "commits_delta_last_run": 0 }, { "full_name": "lsegroup/mnemosyne", "html_url": "https://github.com/lsegroup/mnemosyne", "track": "Push the Frontier", "domain": "Developer Tooling, Infra & Security", "summary": "Git-backed shared memory graph for AI teams with MCP and VSCode access", "readme_summary": "Self-hosted AI team memory storing markdown+YAML nodes in git with SQLite FTS5 + sqlite-vec RRF search. TypeScript monorepo with MCP stdio, Streamable-HTTP and REST facades plus VSCode client. Model-agnostic; uses any OpenAI-compatible gateway for embeddings and optional extract/ask, runs offline otherwise.", "tech_highlights": [ "MCP Server + REST", "SQLite FTS5 + sqlite-vec", "TypeScript Monorepo" ], "created_at": "2026-10-28T13:35:24Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 78, "commits_before_window": 14, "prs_total": 0, "prs_merged": 0, "is_preexisting": true, "has_docker": false, "has_tests": false, "has_src": true, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 1, "score_impact": 2.3, "score_meta_tooling": 0.5, "score_tech_depth": 1.2, "score_demo": 1.0, "score_total": 5.0, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "High-impact domain", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (78)", "+0.6" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 520, "is_new": true, "commits_delta": 78, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "akilanpl/worldspeak", "html_url": "https://github.com/akilanpl/worldspeak", "track": "Build for Your World", "domain": "Voice, Speech & Audio AI", "summary": "Offline bilingual English-Tamil board with exact preview then speech", "readme_summary": "WorldSpeak turns intent into exact English/Tamil preview and speaks only on explicit action with offline support. Monorepo with apps/packages, Supabase JSONB persistence and pixel-mask renderer. Uses Spark/SAM pipeline for scene generation.", "tech_highlights": [ "Muse Spark", "SAM Vision", "Supabase + TypeScript" ], "created_at": "2026-10-27T02:06:59Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 78, "commits_before_window": 0, "prs_total": 17, "prs_merged": 17, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": true, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.5, "score_meta_tooling": 0.8, "score_tech_depth": 1.9, "score_demo": 0.8, "score_total": 5.0, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ] ], "meta": [ [ "Base", "+0.5" ], [ "Muse Spark integration", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (78)", "+0.6" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Automated CI workflow", "+0.2" ], [ "PR review workflow (17 PRs)", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ] ] }, "rank": 521, "is_new": false, "commits_delta": 0, "rank_delta": -312, "commits_delta_last_run": 0 }, { "full_name": "sanggusti/automatic-octo-meme", "html_url": "https://github.com/sanggusti/automatic-octo-meme", "track": "Push the Frontier", "domain": "Robotics, IoT & Manufacturing", "summary": "Benchmarks language models as drone navigators in simulated 3D disaster environments.", "readme_summary": "Simulates forest fire, flood, earthquake and landslide scenarios to test drone navigation and recon advice. Eval harness uses inspect-ai with Baseten and Modal inference and tracked runs. Uses LLMs as agents evaluated on action, perception and metrics.", "tech_highlights": [ "inspect-ai Harness", "Drone Sim Evals", "Baseten + Modal" ], "created_at": "2026-10-19T13:19:53Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 45, "commits_before_window": 1, "prs_total": 22, "prs_merged": 22, "is_preexisting": true, "has_docker": false, "has_tests": true, "has_src": false, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": true, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.3, "score_meta_tooling": 0.5, "score_tech_depth": 1.4, "score_demo": 0.8, "score_total": 5.0, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "High-impact domain", "+0.4" ], [ "Eval & benchmark proof", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ] ], "meta": [ [ "Base", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (45)", "+0.4" ], [ "Automated test suite", "+0.3" ], [ "Agent / eval harness", "+0.2" ], [ "PR review workflow (22 PRs)", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ] ] }, "rank": 522, "is_new": false, "commits_delta": 15, "rank_delta": -129, "commits_delta_last_run": 0 }, { "full_name": "ztdgtll/musez-home", "html_url": "https://github.com/ztdgtll/musez-home", "track": "Build for Your World", "domain": "Voice, Speech & Audio AI", "summary": "Raspberry Pi voice bridge turning spoken requests into answers and wall display scenes", "readme_summary": "Low-latency voice bridge where Meta Model API drives a Pi wall display and speaker. muse-spark-1.3 streams answers with function calls, escalating via internal call to muse-wonder-1.0. Every turn is latency-measured in experiments/results.", "tech_highlights": [ "Muse Spark 1.3", "Muse Wonder 1.0", "Raspberry Pi Bridge" ], "created_at": "2026-10-26T17:30:05Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 25, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": false, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": true, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.9, "score_meta_tooling": 1.6, "score_tech_depth": 0.9, "score_demo": 0.6, "score_total": 5.0, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Eval & benchmark proof", "+0.3" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (25)", "+0.4" ], [ "Agent / eval harness", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 523, "is_new": false, "commits_delta": 15, "rank_delta": -199, "commits_delta_last_run": 0 }, { "full_name": "aitrailblazer/atlas7-filing-sentinel", "html_url": "https://github.com/aitrailblazer/atlas7-filing-sentinel", "track": "Push the Frontier", "domain": "Finance, Crypto & Web3", "summary": "SEC filing grader that also grades models against answer key", "readme_summary": "Evaluation harness with frozen demo-set and grading prompts measuring signal precision and agreement. Reference arm uses Muse Spark 1.3 graded against locked key. Reports 87.7% agreement on 179 filings.", "tech_highlights": [ "Muse Spark 1.3", "Eval Harness", "SEC Signal Grading" ], "created_at": "2026-10-26T19:56:00Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 20, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": false, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": true, "live_urls": [ "https://aitrailblazer.com" ], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.0, "score_meta_tooling": 1.3, "score_tech_depth": 0.7, "score_demo": 1.0, "score_total": 5.0, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "Domain alignment", "+0.3" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (20)", "+0.4" ] ], "demo": [ [ "Base", "+0.4" ], [ "Live web deployment", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 524, "is_new": false, "commits_delta": 5, "rank_delta": -363, "commits_delta_last_run": 0 }, { "full_name": "AnuranjanJain/MetaAI2026", "html_url": "https://github.com/AnuranjanJain/MetaAI2026", "track": "Build for Your World", "domain": "General & Emerging Applications", "summary": "Local-first cozy day planner with visual room and voice task entry", "readme_summary": "Pocketroom shows today's plan as a hand-built SVG room reflecting tasks, wardrobe, and posters. Built with Vite, TypeScript, and local-first storage with voice assistant for adding and querying tasks. Uses Meta AI voice parsing to create reminders and schedule entries.", "tech_highlights": [ "Vite + TypeScript", "SVG Room UI", "Voice Planner" ], "created_at": "2026-10-30T18:22:17Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 20, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": true, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": true, "live_urls": [ "https://anuranjanjain.github.io/MetaAI2026/", "https://pocketroom-six.vercel.app" ], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.7, "score_meta_tooling": 0.8, "score_tech_depth": 1.5, "score_demo": 1.0, "score_total": 5.0, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "General domain", "+0.2" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Muse Spark integration", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (20)", "+0.4" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Automated CI workflow", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Live web deployment", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 525, "is_new": true, "commits_delta": 20, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "panoskokmotos/impact-proof", "html_url": "https://github.com/panoskokmotos/impact-proof", "track": "Build for Your World", "domain": "Healthcare, Civic Tech & Sustainability", "summary": "Turns WhatsApp field photos and voice notes into verified donor reports.", "readme_summary": "Node webhook ingests WhatsApp media, hashes evidence and transcribes voice with muse-voice-transcribe-1.0. Meta Muse drafts source-linked delivery cases for nonprofit review. Donor report shows confirmed vs unproven claims.", "tech_highlights": [ "Muse Drafting", "muse-voice-transcribe-1.0", "WhatsApp Webhook" ], "created_at": "2026-11-01T15:55:34Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 18, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.6, "score_meta_tooling": 1.3, "score_tech_depth": 1.3, "score_demo": 0.8, "score_total": 5.0, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "High-impact domain", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (18)", "+0.4" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ] ] }, "rank": 526, "is_new": true, "commits_delta": 18, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "somossoftgrama/mi-cultivo-me-habla", "html_url": "https://github.com/somossoftgrama/mi-cultivo-me-habla", "track": "Build for Your World", "domain": "Healthcare, Civic Tech & Sustainability", "summary": "Crop photo becomes first-person voice note telling farmers what plants need", "readme_summary": "Farmer uploads crop photo via web app, Muse Spark analyzes it as the plant speaking, ElevenLabs TTS returns a voice note. Stack includes Muse Spark 1.3, planned SAM 3.1 and Muse Image. Python src with static and worker.", "tech_highlights": [ "Muse Spark 1.3", "SAM 3.1 Vision", "ElevenLabs TTS" ], "created_at": "2026-10-26T23:15:52Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 17, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": true, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.4, "score_meta_tooling": 1.8, "score_tech_depth": 1.0, "score_demo": 0.8, "score_total": 5.0, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "High-impact domain", "+0.4" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (17)", "+0.4" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ] ] }, "rank": 527, "is_new": false, "commits_delta": 0, "rank_delta": -285, "commits_delta_last_run": 0 }, { "full_name": "neehanthreddym/bugcapsule", "html_url": "https://github.com/neehanthreddym/bugcapsule", "track": "Push the Frontier", "domain": "Developer Tooling, Infra & Security", "summary": "Turns HAR captures into shareable mock capsules with synthetic data replacing PII", "readme_summary": "FastAPI backend plus frontend that ingests HAR files, strips auth locally and substitutes consistent synthetic data. Verifies reproduction of API failures against a local mock server. Built for debugging without production accounts or AI keys.", "tech_highlights": [ "FastAPI + Frontend", "HAR Mock Server", "Synthetic Data" ], "created_at": "2026-10-28T05:14:37Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 16, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": true, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.1, "score_meta_tooling": 1.3, "score_tech_depth": 1.0, "score_demo": 0.6, "score_total": 5.0, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "High-impact domain", "+0.4" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (16)", "+0.4" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 528, "is_new": false, "commits_delta": 3, "rank_delta": -266, "commits_delta_last_run": 0 }, { "full_name": "FAHMYZAR/dapurstudio", "html_url": "https://github.com/FAHMYZAR/dapurstudio", "track": "Build for Your World", "domain": "Business, Sales & Commerce", "summary": "Turns messy kitchen food photos into catalog photos with cost and caption", "readme_summary": "Uploads dish photo, SAM 3.1 segments plated food with parallel prompts, generates clean catalog image plus ingredient cost estimate and sales caption. End-to-end flow for small sellers with human review before save.", "tech_highlights": [ "SAM 3.1 Vision", "Muse Spark 1.3", "Muse Image" ], "created_at": "2026-10-27T08:24:13Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 12, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": true, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.6, "score_meta_tooling": 1.8, "score_tech_depth": 0.8, "score_demo": 0.8, "score_total": 5.0, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ] ], "tech": [ [ "Base", "+0.3" ], [ "5+ window commits (12)", "+0.2" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ] ] }, "rank": 529, "is_new": false, "commits_delta": 3, "rank_delta": -310, "commits_delta_last_run": 0 }, { "full_name": "Quantumhurst/visual-vocal-builder", "html_url": "https://github.com/Quantumhurst/visual-vocal-builder", "track": "Build for Your World", "domain": "Legal & Compliance", "summary": "Voice-driven incorporation canvas to compare jurisdictions and split equity", "readme_summary": "Next.js app where speech drives interactive incorporation canvas, checklists, and tables via CopilotKit useCoAgent. Uses Muse Voice Transcribe for STT and Muse Spark brain via Meta Model API for state updates and guidance.", "tech_highlights": [ "Muse Voice STT", "Muse Spark 1.3", "Next.js + CopilotKit" ], "created_at": "2026-10-27T17:44:27Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 12, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.5, "score_meta_tooling": 1.6, "score_tech_depth": 1.1, "score_demo": 0.8, "score_total": 5.0, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "5+ window commits (12)", "+0.2" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ] ] }, "rank": 530, "is_new": false, "commits_delta": 6, "rank_delta": -302, "commits_delta_last_run": 0 }, { "full_name": "duschino-source/pocketbench-windows", "html_url": "https://github.com/duschino-source/pocketbench-windows", "track": "Push the Frontier", "domain": "Autonomous Agents & Workflow Automation", "summary": "Windows desktop agent that investigates and repairs OS and app issues", "readme_summary": "Electron Windows 11 app where Muse Spark calls bounded diagnostics, researches fixes via Meta web search, drafts structured repairs and verifies changes. Includes review of sources and affected resources. Built during hackathon Oct 30 2026.", "tech_highlights": [ "Muse Spark", "Electron + Windows", "Meta Web Search" ], "created_at": "2026-10-30T16:06:29Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 12, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": true, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.0, "score_meta_tooling": 1.3, "score_tech_depth": 1.3, "score_demo": 0.4, "score_total": 5.0, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "High-impact domain", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "5+ window commits (12)", "+0.2" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Automated CI workflow", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ] ] }, "rank": 531, "is_new": true, "commits_delta": 12, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "Techfrontiers/snapsell-ai", "html_url": "https://github.com/Techfrontiers/snapsell-ai", "track": "Build for Your World", "domain": "Business, Sales & Commerce", "summary": "Turns one messy phone photo into a ready-to-post product listing card", "readme_summary": "Pipeline locates product with SAM 3.1, cleans background with Muse Image edits, then writes listing copy with Muse Spark 1.3 from visible details only. Demo is bilingual TH/EN gallery with Python PIL server. Built for Thai small sellers in Indie track.", "tech_highlights": [ "SAM 3.1 Vision", "Muse Image Edits", "Muse Spark 1.3" ], "created_at": "2026-10-27T02:12:11Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 5, "commits_before_window": 0, "prs_total": 6, "prs_merged": 2, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": true, "live_urls": [ "https://snapsell-demo.pages.dev/" ], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.3, "score_meta_tooling": 1.8, "score_tech_depth": 1.1, "score_demo": 0.8, "score_total": 5.0, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ] ], "tech": [ [ "Base", "+0.3" ], [ "5+ window commits (5)", "+0.2" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Live web deployment", "+0.4" ] ] }, "rank": 532, "is_new": false, "commits_delta": 0, "rank_delta": -251, "commits_delta_last_run": 0 }, { "full_name": "cybersheik/souls-of-muse", "html_url": "https://github.com/cybersheik/souls-of-muse", "track": "Build for Your World", "domain": "Education & Knowledge Systems", "summary": "Bilingual AI-mediated music lessons to preserve instrumental and singing skills", "readme_summary": "Prototype for teacher-led lessons with a Muse AI mediator and bilingual instruction. Stack is web prototype plus Python harness-bench validator and single-VM runtime controlling up to five simultaneous lessons.", "tech_highlights": [ "Muse AI Mediator", "Python Test Bench", "Web Lesson Prototype" ], "created_at": "2026-10-27T02:52:00Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 4, "commits_before_window": 0, "prs_total": 4, "prs_merged": 1, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": true, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": true, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.8, "score_meta_tooling": 1.1, "score_tech_depth": 1.3, "score_demo": 0.8, "score_total": 5.0, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Eval & benchmark proof", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ] ], "meta": [ [ "Base", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Agent / eval harness", "+0.2" ], [ "Automated CI workflow", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ] ] }, "rank": 533, "is_new": true, "commits_delta": 4, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "loucasty-cell/PeteyPlant", "html_url": "https://github.com/loucasty-cell/PeteyPlant", "track": "Build for Your World", "domain": "General & Emerging Applications", "summary": "Gamified plant-pet app with HP, streaks and real plant-care models", "readme_summary": "PeteyPlant turns houseplants into expressive cartoon pets with HP, XP, streaks and a ReAct explainer. Backend computes VPD, soil moisture decay and light forecasting; provider layer is configurable but no live Muse call in this build.", "tech_highlights": [ "React + Python Backend", "VPD + Forecasting", "ReAct Agent" ], "created_at": "2026-10-26T16:49:44Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 3, "commits_before_window": 0, "prs_total": 1, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": true, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": true, "has_eval_benchmarks": true, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 1, "score_impact": 1.8, "score_meta_tooling": 1.8, "score_tech_depth": 0.8, "score_demo": 0.6, "score_total": 5.0, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "General domain", "+0.2" ], [ "Eval & benchmark proof", "+0.3" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ], [ "Open-weights / fine-tuning", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Agent / eval harness", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 534, "is_new": false, "commits_delta": 0, "rank_delta": -250, "commits_delta_last_run": 0 }, { "full_name": "prakhart111/AgentCom", "html_url": "https://github.com/prakhart111/AgentCom", "track": "Push the Frontier", "domain": "Developer Tooling, Infra & Security", "summary": "Chrome extension plus MCP server letting personal agents collaborate with other AI apps.", "readme_summary": "Connects isolated AI apps via Chrome MV3 extension and MCP stdio server in strict TypeScript. Your coding agent delegates context-aware subtasks to ChatGPT/Gemini/Muse and iterates until correct. Built as multi-LLM interoperable agent tooling for the hackathon.", "tech_highlights": [ "Muse + Multi-LLM", "MCP stdio Server", "Chrome MV3 + TS" ], "created_at": "2026-10-29T07:45:11Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 2, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.3, "score_meta_tooling": 0.8, "score_tech_depth": 0.9, "score_demo": 1.0, "score_total": 5.0, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "High-impact domain", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Muse Spark integration", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 535, "is_new": true, "commits_delta": 2, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "marcohatran/Choom-Meta-Global-AI-Developer-Hackathon", "html_url": "https://github.com/marcohatran/Choom-Meta-Global-AI-Developer-Hackathon", "track": "Build for Your World", "domain": "Education & Knowledge Systems", "summary": "AI IELTS examiner grading Writing and Speaking in 30 seconds", "readme_summary": "Provides IELTS Writing/Speaking grading on four official criteria, study planner, and coach agent. Built with Python, Docker, Cloud Run and structured output. Uses Muse Spark for planning/grading and Muse models for examiner reports.", "tech_highlights": [ "Muse Spark 1.3", "IELTS Rubric Grading", "Python + Cloud Run" ], "created_at": "2026-11-01T07:35:08Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 2, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": true, "has_tests": true, "has_src": true, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.7, "score_meta_tooling": 1.6, "score_tech_depth": 0.9, "score_demo": 0.8, "score_total": 5.0, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Docker packaging", "+0.4" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ] ] }, "rank": 536, "is_new": true, "commits_delta": 2, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "drawmeanelephant/content-upgrades", "html_url": "https://github.com/drawmeanelephant/content-upgrades", "track": "Push the Frontier", "domain": "Developer Tooling, Infra & Security", "summary": "Template loop that upgrades AI markdown with deterministic scoring", "readme_summary": "knap-mcp loop where models fill JSON values while human templates control formatting. Uses Zig MCP server, deterministic density scorer and insert-only guards. Uses Muse models for drafting without allowing layout writes.", "tech_highlights": [ "Muse Models", "Zig + MCP Server", "Deterministic Scorer" ], "created_at": "2026-10-26T19:16:27Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 203, "commits_before_window": 0, "prs_total": 204, "prs_merged": 204, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": true, "has_ci": true, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.0, "score_meta_tooling": 0.5, "score_tech_depth": 1.6, "score_demo": 0.8, "score_total": 4.9, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "High-impact domain", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ] ], "meta": [ [ "Base", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (203)", "+0.6" ], [ "Modular src/ architecture", "+0.3" ], [ "Automated CI workflow", "+0.2" ], [ "PR review workflow (204 PRs)", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ] ] }, "rank": 537, "is_new": true, "commits_delta": 203, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "pajarraco/Sparkl", "html_url": "https://github.com/pajarraco/Sparkl", "track": "Build for Your World", "domain": "Business, Sales & Commerce", "summary": "Marketplace connecting vacation-rental hosts with cleaners", "readme_summary": "Sparkl is a two-sided marketplace with host/cleaner roles, job lifecycle, ranked matching and realtime chat. Built with Expo React Native, Fastify, tRPC and PostgreSQL. Uses Meta AI assistant for job posting from checklists.", "tech_highlights": [ "Expo + React Native", "Fastify + tRPC", "PostgreSQL" ], "created_at": "2026-10-26T08:02:32Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 80, "commits_before_window": 0, "prs_total": 3, "prs_merged": 3, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": true, "has_ci": true, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 1, "score_impact": 1.8, "score_meta_tooling": 0.5, "score_tech_depth": 1.6, "score_demo": 1.0, "score_total": 4.9, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (80)", "+0.6" ], [ "Modular src/ architecture", "+0.3" ], [ "Automated CI workflow", "+0.2" ], [ "PR review workflow (3 PRs)", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 538, "is_new": false, "commits_delta": 37, "rank_delta": -271, "commits_delta_last_run": 0 }, { "full_name": "danielmartinezsarta/vale-meta-hackathon", "html_url": "https://github.com/danielmartinezsarta/vale-meta-hackathon", "track": "Build for Your World", "domain": "Voice, Speech & Audio AI", "summary": "Hands-free voice helper for pricing aimed at nail technicians", "readme_summary": "Next.js TypeScript app with one-tap microphone screen for hands-busy workers. Explains pricing as supplies, time and fixed costs out loud. Built Oct 27 onward during hackathon window.", "tech_highlights": [ "Voice-First UI", "Next.js + TypeScript", "Muse Voice" ], "created_at": "2026-10-26T21:02:56Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 64, "commits_before_window": 0, "prs_total": 7, "prs_merged": 7, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": true, "live_urls": [ "https://vale-meta-hackathon.vercel.app" ], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.5, "score_meta_tooling": 0.5, "score_tech_depth": 1.7, "score_demo": 1.2, "score_total": 4.9, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ] ], "meta": [ [ "Base", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (64)", "+0.6" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "PR review workflow (7 PRs)", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Live web deployment", "+0.4" ] ] }, "rank": 539, "is_new": false, "commits_delta": 42, "rank_delta": -218, "commits_delta_last_run": 0 }, { "full_name": "Bignesh14/glimmer-m5-selftune", "html_url": "https://github.com/Bignesh14/glimmer-m5-selftune", "track": "Push the Frontier", "domain": "Developer Tooling, Infra & Security", "summary": "Self-tuning loop making Muse Glimmer 30B faster on M5 Max via Metal kernels", "readme_summary": "Measures Muse Glimmer 30B 4-bit on Mac Studio M5 Max via MLX and adds exact prompt-lookup decoding. Implements H8 sliding-window fix and H9 attention-kernel fix with replicated benchmarks. Reports +17% coding and 1.15x Spec-Bench gains.", "tech_highlights": [ "Muse Glimmer 30B", "MLX + Metal", "Spec-Bench Eval" ], "created_at": "2026-10-26T10:25:54Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 44, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": false, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": true, "has_eval_benchmarks": true, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.4, "score_meta_tooling": 1.0, "score_tech_depth": 0.9, "score_demo": 0.6, "score_total": 4.9, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "High-impact domain", "+0.4" ], [ "Eval & benchmark proof", "+0.3" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Open-weights / fine-tuning", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (44)", "+0.4" ], [ "Agent / eval harness", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 540, "is_new": false, "commits_delta": 28, "rank_delta": -237, "commits_delta_last_run": 0 }, { "full_name": "SalChicanoLoco/quetzal-aoi-briefing", "html_url": "https://github.com/SalChicanoLoco/quetzal-aoi-briefing", "track": "Push the Frontier", "domain": "General & Emerging Applications", "summary": "Turns live seismic telemetry into mapped areas of interest with AI briefings", "readme_summary": "Takes live seismic telemetry, derives areas of interest polygons, visualizes with SAM, and generates Muse Spark briefings. Separates measured, calculated, and inferred values with sources. Viewer plus GIS pipeline built for testable geophysical analysis.", "tech_highlights": [ "SAM Visualization", "Muse Spark 1.3", "GIS + Viewer" ], "created_at": "2026-10-26T17:31:29Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 38, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.9, "score_meta_tooling": 1.1, "score_tech_depth": 1.3, "score_demo": 0.6, "score_total": 4.9, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "General domain", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (38)", "+0.4" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 541, "is_new": true, "commits_delta": 38, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "Liamostudio/Pathfinder", "html_url": "https://github.com/Liamostudio/Pathfinder", "track": "Push the Frontier", "domain": "Robotics, IoT & Manufacturing", "summary": "Tabletop SO-101 robot arm for safe pick-and-place around people", "readme_summary": "Look-and-Pick is a table-mounted SO-101 arm where Meta models perceive and plan but never drive motors directly. Uses SAM 3.1 for tracking, ArUco calibration, plus a checkable speed-and-separation safety layer. Python orchestrator with simulation GUI and fake adapters.", "tech_highlights": [ "SAM 3.1 Vision", "SO-101 Robot Arm", "Python Safety Layer" ], "created_at": "2026-10-27T13:11:49Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 37, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.0, "score_meta_tooling": 0.8, "score_tech_depth": 1.3, "score_demo": 0.8, "score_total": 4.9, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "High-impact domain", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ] ], "meta": [ [ "Base", "+0.5" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (37)", "+0.4" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ] ] }, "rank": 542, "is_new": false, "commits_delta": 1, "rank_delta": -227, "commits_delta_last_run": 0 }, { "full_name": "ainovo/extbrain-meta", "html_url": "https://github.com/ainovo/extbrain-meta", "track": "Build for Your World", "domain": "General & Emerging Applications", "summary": "Local organizer that cures AI chat amnesia without traditional RAG", "readme_summary": "ExtBrain organizes tens of thousands of chats across AIs to recover decisions and insights. Web app with Docker and Cloud Run, takeout importer. Built with Meta Muse Code, local-first anti-RAG approach.", "tech_highlights": [ "Muse Code built", "Local-first memory", "Docker Cloud Run" ], "created_at": "2026-10-26T21:03:27Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 33, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": true, "has_tests": true, "has_src": true, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 3, "score_impact": 1.8, "score_meta_tooling": 1.0, "score_tech_depth": 1.3, "score_demo": 0.8, "score_total": 4.9, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "General domain", "+0.2" ], [ "Docker packaging", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (33)", "+0.4" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ] ] }, "rank": 543, "is_new": true, "commits_delta": 33, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "Abeltrust/kulturegram", "html_url": "https://github.com/Abeltrust/kulturegram", "track": "Build for Your World", "domain": "Healthcare, Civic Tech & Sustainability", "summary": "Cultural heritage platform to document traditions, timelines and private vaults", "readme_summary": "Laravel PHP app for submitting and moderating cultural practices, timelines, gatherings and vaults. Stack includes admin review center, search by region and endangerment, plus docs for cultural AI system. Uses Meta AI for cultural content processing.", "tech_highlights": [ "Laravel PHP", "Timeline + Vaults", "Cultural AI System" ], "created_at": "2026-10-26T22:34:15Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 33, "commits_before_window": 50, "prs_total": 0, "prs_merged": 0, "is_preexisting": true, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": true, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.2, "score_meta_tooling": 0.5, "score_tech_depth": 1.2, "score_demo": 1.0, "score_total": 4.9, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "High-impact domain", "+0.4" ], [ "Eval & benchmark proof", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (33)", "+0.4" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Agent / eval harness", "+0.2" ], [ "Pre-Oct 26 commits dominate (50)", "-0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 544, "is_new": false, "commits_delta": 5, "rank_delta": -284, "commits_delta_last_run": 0 }, { "full_name": "Mirai-Climbing/topo-agent", "html_url": "https://github.com/Mirai-Climbing/topo-agent", "track": "Build for Your World", "domain": "Gaming, Entertainment & Creative Media", "summary": "Photo-based bouldering topo builder that maps climbing problems for gyms", "readme_summary": "Snap a wall photo, tap one hold, SAM 3.1 segments all holds. A Muse Spark tool-using agent inspects, compares and zooms to select same-problem holds. Output topo is shareable in Mirai Climbing app, aiding colorblind climbers.", "tech_highlights": [ "SAM 3.1 Vision", "Muse Spark Agent", "Python Tool Use" ], "created_at": "2026-10-26T19:06:54Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 32, "commits_before_window": 0, "prs_total": 17, "prs_merged": 9, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": false, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.5, "score_meta_tooling": 1.6, "score_tech_depth": 1.2, "score_demo": 0.6, "score_total": 4.9, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "General domain", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (32)", "+0.4" ], [ "Automated test suite", "+0.3" ], [ "PR review workflow (9 PRs)", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 545, "is_new": true, "commits_delta": 32, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "Adri-El/markwise", "html_url": "https://github.com/Adri-El/markwise", "track": "Build for Your World", "domain": "Education & Knowledge Systems", "summary": "Lecturer-approved rubric tool that drafts marks with quoted student evidence.", "readme_summary": "Lecturers create assignments, students submit typed or PDF scripts transcribed with [illegible] marks. Model drafts rubric for approval then marks only against it. Stack spans web frontend plus worker and evals.", "tech_highlights": [ "Muse Text Models", "Rubric-Grounded Marking", "Web + Worker" ], "created_at": "2026-10-28T18:27:27Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 32, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": false, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": true, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.9, "score_meta_tooling": 1.3, "score_tech_depth": 0.9, "score_demo": 0.8, "score_total": 4.9, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Eval & benchmark proof", "+0.3" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (32)", "+0.4" ], [ "Agent / eval harness", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ] ] }, "rank": 546, "is_new": true, "commits_delta": 32, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "mohamedabdelnasser7-gif/ascent-learning-agents", "html_url": "https://github.com/mohamedabdelnasser7-gif/ascent-learning-agents", "track": "Build for Your World", "domain": "Business, Sales & Commerce", "summary": "WhatsApp storefront agent in Arabic, English and Franco that learns.", "readme_summary": "WhatsApp-first sales inbox that answers from real product, size and stock data with price validation. Supports Egyptian Arabic, English, Franco text and voice notes with human handoff. Adds learning loop over real sales results.", "tech_highlights": [ "WhatsApp Agent", "Multilingual NLP", "Learning Loop" ], "created_at": "2026-10-27T02:23:44Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 31, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": false, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": true, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.8, "score_meta_tooling": 1.3, "score_tech_depth": 1.0, "score_demo": 0.8, "score_total": 4.9, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "Open-weights / fine-tuning", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (31)", "+0.4" ], [ "Automated test suite", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ] ] }, "rank": 547, "is_new": false, "commits_delta": 28, "rank_delta": -84, "commits_delta_last_run": 0 }, { "full_name": "tsetse012/60-second-fire-check", "html_url": "https://github.com/tsetse012/60-second-fire-check", "track": "Build for Your World", "domain": "Healthcare, Civic Tech & Sustainability", "summary": "Walks corridors with phone video to generate fire-safety self-inspection report", "readme_summary": "Upload a corridor walk video to detect fire-door, extinguisher and escape-route issues with timestamps. Pipeline plus rulesets produce manager email and uncertain-item list. Uses Meta AI vision models for inspection.", "tech_highlights": [ "Video Vision Analysis", "Python Pipeline Rules", "Fire Safety Checklist" ], "created_at": "2026-10-27T22:49:11Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 30, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": true, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": true, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.0, "score_meta_tooling": 1.1, "score_tech_depth": 1.2, "score_demo": 0.6, "score_total": 4.9, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "High-impact domain", "+0.4" ], [ "Eval & benchmark proof", "+0.3" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (30)", "+0.4" ], [ "Modular src/ architecture", "+0.3" ], [ "Agent / eval harness", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 548, "is_new": false, "commits_delta": 0, "rank_delta": -337, "commits_delta_last_run": 0 }, { "full_name": "ultron513/pit-wall", "html_url": "https://github.com/ultron513/pit-wall", "track": "Build for Your World", "domain": "Gaming, Entertainment & Creative Media", "summary": "Local autonomous F1 race strategist that simulates pit stops from timing data", "readme_summary": "Pulls F1 timing data, fits tyre and fuel pace model and searches one and two-stop plans for undercut threats. Planner runs on Muse Glimmer 30B locally via Ollama while hand-written engine does math. Python with tests and scripts.", "tech_highlights": [ "Muse Glimmer 30B", "Ollama Local Inference", "Tyre-Fuel Simulation" ], "created_at": "2026-10-30T17:43:29Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 30, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": true, "has_eval_benchmarks": true, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.8, "score_meta_tooling": 1.0, "score_tech_depth": 1.5, "score_demo": 0.6, "score_total": 4.9, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "General domain", "+0.2" ], [ "Eval & benchmark proof", "+0.3" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Open-weights / fine-tuning", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (30)", "+0.4" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Agent / eval harness", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 549, "is_new": true, "commits_delta": 30, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "alper-tekin/trafik-ikizi", "html_url": "https://github.com/alper-tekin/trafik-ikizi", "track": "Build for Your World", "domain": "Healthcare, Civic Tech & Sustainability", "summary": "Turns intersection camera video into calibrated simulation to test signal timing", "readme_summary": "Converts fixed-camera intersection video into calibrated traffic simulation using SAM 3.1 detections. Muse Spark agent tests signal timings and backs claims with measured counts. Includes Python pipeline and web viewer.", "tech_highlights": [ "SAM 3.1 Vision", "Muse Spark Agent", "Traffic Simulation" ], "created_at": "2026-10-31T10:39:44Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 27, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": true, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.7, "score_meta_tooling": 1.6, "score_tech_depth": 1.0, "score_demo": 0.6, "score_total": 4.9, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "High-impact domain", "+0.4" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (27)", "+0.4" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 550, "is_new": true, "commits_delta": 27, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "NestroyMusoke/WALK-IT", "html_url": "https://github.com/NestroyMusoke/WALK-IT", "track": "Build for Your World", "domain": "Multimodal Vision & Video (SAM / Vision)", "summary": "Shareable camera-guided walking routes with verified AR directions", "readme_summary": "Planned system where one user records a route once and another follows verified AR directions to the exact destination. Intended pipeline is Muse Spark to SAM 3.1 fused with geometric evidence, with static replay explorer.", "tech_highlights": [ "Muse Spark", "SAM 3.1 Vision", "AR Navigation" ], "created_at": "2026-10-26T21:04:37Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 27, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": true, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": true, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.8, "score_meta_tooling": 1.1, "score_tech_depth": 1.2, "score_demo": 0.8, "score_total": 4.9, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Eval & benchmark proof", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ] ], "meta": [ [ "Base", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (27)", "+0.4" ], [ "Modular src/ architecture", "+0.3" ], [ "Agent / eval harness", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ] ] }, "rank": 551, "is_new": true, "commits_delta": 27, "rank_delta": 0, "commits_delta_last_run": 1 }, { "full_name": "samuelbukumni/unhook", "html_url": "https://github.com/samuelbukumni/unhook", "track": "Build for Your World", "domain": "Finance, Crypto & Web3", "summary": "Subscription tracker that extracts renewals from receipts and warns early", "readme_summary": "Paste receipt or checkout page to extract service, price and trial dates for review and localStorage tracking. Next.js pages plus /api/extract route with reminders and cancel guides. Uses Muse Spark for receipt extraction.", "tech_highlights": [ "Muse Spark", "Next.js + API Route", "localStorage" ], "created_at": "2026-10-27T21:39:08Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 22, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": true, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.6, "score_meta_tooling": 1.3, "score_tech_depth": 1.0, "score_demo": 1.0, "score_total": 4.9, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (22)", "+0.4" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 552, "is_new": false, "commits_delta": 17, "rank_delta": -188, "commits_delta_last_run": 0 }, { "full_name": "GoldSpur/ccc-learning-lab-hackathon", "html_url": "https://github.com/GoldSpur/ccc-learning-lab-hackathon", "track": "Build for Your World", "domain": "Education & Knowledge Systems", "summary": "Guided homework resilience prototype with safety stops and provenance labels.", "readme_summary": "Childhood Confidence Learning Lab runs locally via Node server with no live API calls. Web prototype with recorded Muse Spark 1.3 responses and mocked tests. Enforces provenance labels, fallback presets and parent override.", "tech_highlights": [ "Muse Spark 1.3", "Node.js Server", "Provenance + Safety" ], "created_at": "2026-10-27T00:02:34Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 18, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.8, "score_meta_tooling": 0.8, "score_tech_depth": 1.3, "score_demo": 1.0, "score_total": 4.9, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Muse Spark integration", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (18)", "+0.4" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 553, "is_new": false, "commits_delta": 1, "rank_delta": -335, "commits_delta_last_run": 0 }, { "full_name": "zxreigns/take-two", "html_url": "https://github.com/zxreigns/take-two", "track": "Build for Your World", "domain": "Gaming, Entertainment & Creative Media", "summary": "Converts client voice notes into tracked video edits exportable to NLE timelines", "readme_summary": "Parses client voice notes into edit plans with Muse Spark, locates moments and tracks objects frame-by-frame with SAM 3.1. Produces approvable proposed edits and NLE timeline export. Frontend plus backend with docs and demo assets.", "tech_highlights": [ "SAM 3.1 Tracking", "Muse Spark 1.3", "Voice-to-Edit" ], "created_at": "2026-10-31T13:50:53Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 16, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": true, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": true, "has_eval_benchmarks": false, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.5, "score_meta_tooling": 1.8, "score_tech_depth": 1.0, "score_demo": 0.6, "score_total": 4.9, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "General domain", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ], [ "Open-weights / fine-tuning", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (16)", "+0.4" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 554, "is_new": true, "commits_delta": 16, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "ilGentEAcutoO/krai-a-beta", "html_url": "https://github.com/ilGentEAcutoO/krai-a-beta", "track": "Build for Your World", "domain": "Voice, Speech & Audio AI", "summary": "Thai voice agent that answers suspect scam calls and alerts family before money moves", "readme_summary": "AI receptionist for elderly Thai parents that screens calls live and triggers family alerts. Built with a Worker plus voice relay, Spark/Wonder per-turn judges, policy and trap mode. Uses Muse Spark, Muse Wonder and Muse Voice Transcribe.", "tech_highlights": [ "Muse Spark", "Muse Wonder", "Muse Voice Transcribe" ], "created_at": "2026-10-26T19:01:14Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 15, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": true, "has_ci": true, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.3, "score_meta_tooling": 1.6, "score_tech_depth": 1.2, "score_demo": 0.8, "score_total": 4.9, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (15)", "+0.4" ], [ "Modular src/ architecture", "+0.3" ], [ "Automated CI workflow", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ] ] }, "rank": 555, "is_new": false, "commits_delta": 9, "rank_delta": -310, "commits_delta_last_run": 0 }, { "full_name": "idrissa-gif/ObjectJEPA", "html_url": "https://github.com/idrissa-gif/ObjectJEPA", "track": "Push the Frontier", "domain": "Multimodal Vision & Video (SAM / Vision)", "summary": "Predicts future object motion in latent space to answer what-if physics questions.", "readme_summary": "Watches CLEVRER videos and forecasts future latents instead of pixels. Stacks frozen V-JEPA 2 encoder with transformer predictor plus SAM 3 object masks and collision head. Muse Spark agent uses world model as tool for predictive queries.", "tech_highlights": [ "V-JEPA 2 Frozen", "SAM 3 Masks", "Muse Spark Agent" ], "created_at": "2026-10-26T23:14:23Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 14, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": false, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.2, "score_meta_tooling": 1.6, "score_tech_depth": 0.5, "score_demo": 0.6, "score_total": 4.9, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "Domain alignment", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "5+ window commits (14)", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 556, "is_new": false, "commits_delta": 8, "rank_delta": -383, "commits_delta_last_run": 0 }, { "full_name": "jccarrascov-sudo/pantallita", "html_url": "https://github.com/jccarrascov-sudo/pantallita", "track": "Build for Your World", "domain": "General & Emerging Applications", "summary": "Recalls last 10 minutes of screen and audio to answer questions", "readme_summary": "Python companion that buffers screenshots every 2s with change detection and transcribes loopback audio with faster-whisper. Muse Spark 1.3 answers what just happened; future SAM 3 grounding for UI actions.", "tech_highlights": [ "Muse Spark 1.3", "Python + mss Capture", "faster-whisper Audio" ], "created_at": "2026-10-31T05:25:56Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 13, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.4, "score_meta_tooling": 1.6, "score_tech_depth": 1.1, "score_demo": 0.8, "score_total": 4.9, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "General domain", "+0.2" ], [ "Multi-module scope (>10 files)", "+0.2" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "5+ window commits (13)", "+0.2" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ] ] }, "rank": 557, "is_new": true, "commits_delta": 13, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "ahaan001/twinfit", "html_url": "https://github.com/ahaan001/twinfit", "track": "Push the Frontier", "domain": "Robotics, IoT & Manufacturing", "summary": "Phone video of a mechanism turned into a verified MuJoCo simulation twin", "readme_summary": "Films a mechanism on ChArUco board, proposes parts with Muse Wonder, segments with SAM 3.1, fits joints and dynamics. Issues trust certificate for MuJoCo model with agent repair. Python CLI with uv.", "tech_highlights": [ "SAM 3.1 Vision", "Muse Wonder", "MuJoCo + Python" ], "created_at": "2026-10-31T17:36:23Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 13, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": true, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.0, "score_meta_tooling": 0.8, "score_tech_depth": 1.3, "score_demo": 0.8, "score_total": 4.9, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "High-impact domain", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ] ], "meta": [ [ "Base", "+0.5" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "5+ window commits (13)", "+0.2" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Automated CI workflow", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ] ] }, "rank": 558, "is_new": true, "commits_delta": 13, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "devinwarp/facade-mapper-intel", "html_url": "https://github.com/devinwarp/facade-mapper-intel", "track": "Build for Your World", "domain": "Gaming, Entertainment & Creative Media", "summary": "Maps building facades from a photo to plan projection shows that fit architecture", "readme_summary": "Standalone Python service that segments facade elements with SAM 3.1, plans readable shows with Muse Spark, and generates per-element visuals with Muse Image. Custom code animates content along outlines; served via FastAPI on Render.", "tech_highlights": [ "SAM 3.1 Vision", "Muse Spark", "Muse Image" ], "created_at": "2026-10-31T07:03:29Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 9, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.2, "score_meta_tooling": 1.8, "score_tech_depth": 1.1, "score_demo": 0.8, "score_total": 4.9, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "General domain", "+0.2" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ] ], "tech": [ [ "Base", "+0.3" ], [ "5+ window commits (9)", "+0.2" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ] ] }, "rank": 559, "is_new": true, "commits_delta": 9, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "kimdooo-a/callreader", "html_url": "https://github.com/kimdooo-a/callreader", "track": "Push the Frontier", "domain": "Developer Tooling, Infra & Security", "summary": "Grant-call reader that answers only with quotable clauses and verified citations", "readme_summary": "CallReader fetches pages and attachments, sniffs bytes to avoid silent unread-as-absent errors. Uses Muse Spark vision transcription and extraction with a citation verifier that abstains without quotes. Enforces invariants for AI rules and eligibility.", "tech_highlights": [ "Muse Spark Vision", "Citation Verifier", "Python Agent" ], "created_at": "2026-10-27T04:06:14Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 8, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.8, "score_meta_tooling": 1.6, "score_tech_depth": 1.1, "score_demo": 0.4, "score_total": 4.9, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "High-impact domain", "+0.4" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "5+ window commits (8)", "+0.2" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ] ] }, "rank": 560, "is_new": false, "commits_delta": 0, "rank_delta": -283, "commits_delta_last_run": 0 }, { "full_name": "Lerdin09/bankao-meta-hackathon", "html_url": "https://github.com/Lerdin09/bankao-meta-hackathon", "track": "Build for Your World", "domain": "Finance, Crypto & Web3", "summary": "Demo digital wallet for sending money between Angola and the world", "readme_summary": "FastAPI + SQLite ledger backend with pure HTML/CSS/JS frontend for transfers and auth via JWT. Includes Copilot assistant over Meta Model API with local fallback when no key is set. Run via uvicorn with pytest coverage and built index page.", "tech_highlights": [ "FastAPI + SQLite", "HTML/CSS/JS Frontend", "Meta Model API Copilot" ], "created_at": "2026-10-27T20:12:03Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 7, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.8, "score_meta_tooling": 1.0, "score_tech_depth": 1.1, "score_demo": 1.0, "score_total": 4.9, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "5+ window commits (7)", "+0.2" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 561, "is_new": false, "commits_delta": 4, "rank_delta": -313, "commits_delta_last_run": 0 }, { "full_name": "vmbr068/netmedic", "html_url": "https://github.com/vmbr068/netmedic", "track": "Push the Frontier", "domain": "Developer Tooling, Infra & Security", "summary": "Autonomous agent that detects BGP faults and runs safe network remediation.", "readme_summary": "Autonomous NetOps agent that diagnoses incidents like BGP failures from inventory and runbooks. Python CLI with Nix + uv, YAML inventory, encrypted secrets. Uses Muse Spark via Meta Model API for detection and remediation.", "tech_highlights": [ "Muse Spark", "Python CLI + uv", "Nix + SOPS" ], "created_at": "2026-10-27T17:01:31Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 5, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": true, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 1, "score_impact": 2.0, "score_meta_tooling": 1.3, "score_tech_depth": 0.8, "score_demo": 0.8, "score_total": 4.9, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "High-impact domain", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "5+ window commits (5)", "+0.2" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ] ] }, "rank": 562, "is_new": false, "commits_delta": 0, "rank_delta": -282, "commits_delta_last_run": 0 }, { "full_name": "jemankalita/opurnos", "html_url": "https://github.com/jemankalita/opurnos", "track": "Build for Your World", "domain": "Autonomous Agents & Workflow Automation", "summary": "Watches hackathons and jobs, matches them to your resume with cited evidence", "readme_summary": "Agent that parses resume PDFs into profiles, checks opportunities for eligibility and scam risk, and emails digests. Built with Next.js, Drizzle and Docker, Pro billing via Razorpay, AI runs on OpenAI models.", "tech_highlights": [ "OpenAI Models", "Next.js + Drizzle", "Razorpay + Email" ], "created_at": "2026-10-28T13:59:59Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 5, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": true, "has_tests": true, "has_src": true, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.3, "score_meta_tooling": 0.5, "score_tech_depth": 1.1, "score_demo": 1.0, "score_total": 4.9, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "High-impact domain", "+0.4" ], [ "Docker packaging", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "5+ window commits (5)", "+0.2" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 563, "is_new": false, "commits_delta": 1, "rank_delta": -299, "commits_delta_last_run": 1 }, { "full_name": "mherick/shichinin", "html_url": "https://github.com/mherick/shichinin", "track": "Push the Frontier", "domain": "Developer Tooling, Infra & Security", "summary": "Chrome extension that poisons trackers with rotating fictional personas", "readme_summary": "Chrome extension that runs decoy browsing and searches as seven fictional adults to corrupt ad profiles. Built from scratch in JS with persona rotation and scheduling, designed during Meta hackathon.", "tech_highlights": [ "Chrome Extension", "Persona Rotation", "Privacy by Noise" ], "created_at": "2026-10-30T15:02:36Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 4, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.1, "score_meta_tooling": 1.3, "score_tech_depth": 0.9, "score_demo": 0.6, "score_total": 4.9, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "High-impact domain", "+0.4" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 564, "is_new": true, "commits_delta": 4, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "bubblesdev/apprentice", "html_url": "https://github.com/bubblesdev/apprentice", "track": "Build for Your World", "domain": "Education & Knowledge Systems", "summary": "Turns expert video into verified guides and watches beginners to catch errors", "readme_summary": "Captures expert hands-on work as verified step-by-step guides, then monitors beginners via phone camera. Built with Muse Spark for step parsing, SAM 3.1 for part/tool tracking, and Muse Voice Transcribe for narration.", "tech_highlights": [ "SAM 3.1 Vision", "Muse Spark", "Muse Voice Transcribe" ], "created_at": "2026-10-26T18:58:27Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 2, "commits_before_window": 0, "prs_total": 1, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": true, "has_ci": true, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.5, "score_meta_tooling": 1.8, "score_tech_depth": 0.8, "score_demo": 0.8, "score_total": 4.9, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ] ], "tech": [ [ "Base", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Automated CI workflow", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ] ] }, "rank": 565, "is_new": false, "commits_delta": 0, "rank_delta": -331, "commits_delta_last_run": 0 }, { "full_name": "himomohi/cutcopy", "html_url": "https://github.com/himomohi/cutcopy", "track": "Build for Your World", "domain": "Business, Sales & Commerce", "summary": "Turns one product photo into cutout, staged scenes and SEO listing", "readme_summary": "Vite React TypeScript app at cutcopy.pages.dev that turns a phone photo into cutout, scene variants, title and description. Uses SAM 3.1 for segmentation, muse-image-1.0 for scenes, muse-spark-1.3 for copy via Meta Model API.", "tech_highlights": [ "SAM 3.1 Vision", "muse-image-1.0", "muse-spark-1.3" ], "created_at": "2026-10-27T00:49:43Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 2, "commits_before_window": 0, "prs_total": 1, "prs_merged": 1, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": true, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": true, "live_urls": [ "https://cutcopy.pages.dev" ], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.5, "score_meta_tooling": 1.6, "score_tech_depth": 0.6, "score_demo": 1.2, "score_total": 4.9, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Live web deployment", "+0.4" ] ] }, "rank": 566, "is_new": false, "commits_delta": 0, "rank_delta": -301, "commits_delta_last_run": 0 }, { "full_name": "Humank1nd/life-itself-manhattan", "html_url": "https://github.com/Humank1nd/life-itself-manhattan", "track": "Push the Frontier", "domain": "Gaming, Entertainment & Creative Media", "summary": "Browser life sim grounded on real Manhattan building data from NYC Open Data.", "readme_summary": "Life Itself Manhattan streams 45k+ NYC building footprints and attributes into a browser simulation. Built with web 3D Cesium plus data pipelines on Firebase. Uses Meta models to reason and act on the real grounded place.", "tech_highlights": [ "NYC Open Data + Cesium", "Browser 3D Sim", "Muse Spark 1.3" ], "created_at": "2026-10-28T17:13:46Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 140, "commits_before_window": 0, "prs_total": 36, "prs_merged": 18, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": true, "has_ci": true, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.1, "score_meta_tooling": 0.5, "score_tech_depth": 1.6, "score_demo": 0.6, "score_total": 4.8, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "General domain", "+0.2" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (140)", "+0.6" ], [ "Modular src/ architecture", "+0.3" ], [ "Automated CI workflow", "+0.2" ], [ "PR review workflow (18 PRs)", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 567, "is_new": false, "commits_delta": 59, "rank_delta": -378, "commits_delta_last_run": 0 }, { "full_name": "BoxLogoDev/argus-counts", "html_url": "https://github.com/BoxLogoDev/argus-counts", "track": "Build for Your World", "domain": "Robotics, IoT & Manufacturing", "summary": "Terminal warehouse cycle counter that photographs bins and reconciles counts", "readme_summary": "Argus photographs warehouse bins from terminal flow, counts with SAM 3.1 via Meta Model API, then reconciles against ledger. Stack is terminal Python plus web console with mock adapters and QA harness. Live counting validated on synthetic images.", "tech_highlights": [ "SAM 3.1 Vision", "Meta Model API", "Pi 5 + Console" ], "created_at": "2026-10-27T10:02:52Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 138, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": false, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.7, "score_meta_tooling": 1.3, "score_tech_depth": 1.2, "score_demo": 0.6, "score_total": 4.8, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "High-impact domain", "+0.4" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (138)", "+0.6" ], [ "Automated test suite", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 568, "is_new": false, "commits_delta": 90, "rank_delta": -388, "commits_delta_last_run": 1 }, { "full_name": "Grateful-Ed/witness", "html_url": "https://github.com/Grateful-Ed/witness", "track": "Build for Your World", "domain": "Voice, Speech & Audio AI", "summary": "Voice-driven warehouse check that verifies spoken receipts against pallet photos", "readme_summary": "Receiver speaks shipment details while system checks pallet photo as Agree/Flag/Cant verify. Static web app on Cloudflare Workers with human sign-off for OS&D reports. Built for hackathon with voice plus vision interaction for warehouse work.", "tech_highlights": [ "Voice + Vision Check", "Cloudflare Workers", "Static JS App" ], "created_at": "2026-10-26T16:47:56Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 102, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": false, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": true, "live_urls": [ "https://grateful-ed.github.io/witness/", "https://grateful-ed.github.io/witness/warehouse.html" ], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.8, "score_meta_tooling": 0.8, "score_tech_depth": 1.2, "score_demo": 1.0, "score_total": 4.8, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Muse Spark integration", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (102)", "+0.6" ], [ "Automated test suite", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Live web deployment", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 569, "is_new": false, "commits_delta": 99, "rank_delta": -157, "commits_delta_last_run": 2 }, { "full_name": "Techfrontiers/snapsell-ww", "html_url": "https://github.com/Techfrontiers/snapsell-ww", "track": "Build for Your World", "domain": "Business, Sales & Commerce", "summary": "Product photo turned into studio listing card for global sellers", "readme_summary": "Brainstorm repo for worldwide seller tool. Pipeline cuts out product with SAM 3.1, creates studio shot with Muse Image, writes copy with Muse Spark. Targets Shopee, Etsy, eBay and Shopify.", "tech_highlights": [ "SAM 3.1 Vision", "Muse Image", "Muse Spark" ], "created_at": "2026-10-28T12:32:20Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 65, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": false, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": true, "live_urls": [ "https://snapsell-demo.pages.dev/." ], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.3, "score_meta_tooling": 1.8, "score_tech_depth": 0.9, "score_demo": 0.8, "score_total": 4.8, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (65)", "+0.6" ] ], "demo": [ [ "Base", "+0.4" ], [ "Live web deployment", "+0.4" ] ] }, "rank": 570, "is_new": false, "commits_delta": 0, "rank_delta": -313, "commits_delta_last_run": 0 }, { "full_name": "Darthfranco/MERLIN", "html_url": "https://github.com/Darthfranco/MERLIN", "track": "Build for Your World", "domain": "Voice, Speech & Audio AI", "summary": "Voice-first home assistant that learns routines and controls devices via app", "readme_summary": "Voice-first Jarvis-style assistant for home tasks with companion app and Blender 3D avatar assets. Uses Meta models for dialogue and device/service orchestration. Includes character clips, room assets and deployment scaffolding.", "tech_highlights": [ "Muse Models", "Voice Interface", "Blender + App" ], "created_at": "2026-10-26T17:53:45Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 47, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": true, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.8, "score_meta_tooling": 0.5, "score_tech_depth": 1.5, "score_demo": 1.0, "score_total": 4.8, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (47)", "+0.4" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Automated CI workflow", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 571, "is_new": false, "commits_delta": 6, "rank_delta": -390, "commits_delta_last_run": 0 }, { "full_name": "ToXMon/soulbound", "html_url": "https://github.com/ToXMon/soulbound", "track": "Build for Your World", "domain": "Gaming, Entertainment & Creative Media", "summary": "Persistent voice+vision AI character with on-chain memory and wallet", "readme_summary": "LiveKit voice loop with Muse Voice Transcribe to Muse Spark muse-spark-1.3 for replies, plus vision. Stores memory lineage on Solana and self-pays inference via x402/Base. pnpm monorepo with Next.js app, agent worker and Solana programs.", "tech_highlights": [ "Muse Spark 1.3", "LiveKit Voice + Vision", "Solana + x402/Base" ], "created_at": "2026-10-26T21:25:17Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 40, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": true, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": true, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.7, "score_meta_tooling": 1.1, "score_tech_depth": 1.2, "score_demo": 0.8, "score_total": 4.8, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "General domain", "+0.2" ], [ "Eval & benchmark proof", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ] ], "meta": [ [ "Base", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (40)", "+0.4" ], [ "Modular src/ architecture", "+0.3" ], [ "Agent / eval harness", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ] ] }, "rank": 572, "is_new": false, "commits_delta": 12, "rank_delta": -255, "commits_delta_last_run": 0 }, { "full_name": "thibaudcathala/meta-hackathon-2026", "html_url": "https://github.com/thibaudcathala/meta-hackathon-2026", "track": "Push the Frontier", "domain": "Developer Tooling, Infra & Security", "summary": "Synthetic user crowd that usability-tests websites in real browsers", "readme_summary": "Footfall recruits personas with Muse Spark to match site audience, then drives real Chrome to complete tasks thinking aloud. Shop database scores success and journals become ranked friction points with quotes and screenshots. Python-based with scenarios, tutorials and tests.", "tech_highlights": [ "Muse Spark Personas", "Real Chrome Automation", "Usability Eval Harness" ], "created_at": "2026-10-26T08:19:40Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 40, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": false, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.1, "score_meta_tooling": 1.1, "score_tech_depth": 1.0, "score_demo": 0.6, "score_total": 4.8, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "High-impact domain", "+0.4" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (40)", "+0.4" ], [ "Automated test suite", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 573, "is_new": false, "commits_delta": 0, "rank_delta": -363, "commits_delta_last_run": 0 }, { "full_name": "DenizYunus/athena", "html_url": "https://github.com/DenizYunus/athena", "track": "Build for Your World", "domain": "Education & Knowledge Systems", "summary": "Camera-verified skill marketplace that guides home repairs step by step.", "readme_summary": "Athena lets experts record repairs into checkable skills with safety gates. Mobile and backend guide users via phone camera or Ray-Ban Meta glasses. Uses Muse Spark for skill compilation and SAM 3.1 for photo step verification.", "tech_highlights": [ "Muse Spark", "SAM 3.1 Vision", "Ray-Ban Meta + Mobile" ], "created_at": "2026-10-27T15:43:41Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 18, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": true, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.6, "score_meta_tooling": 1.6, "score_tech_depth": 1.0, "score_demo": 0.6, "score_total": 4.8, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (18)", "+0.4" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 574, "is_new": false, "commits_delta": 12, "rank_delta": -402, "commits_delta_last_run": 0 }, { "full_name": "mdbaasim/agent-workflow-security", "html_url": "https://github.com/mdbaasim/agent-workflow-security", "track": "Push the Frontier", "domain": "Developer Tooling, Infra & Security", "summary": "Objective-aware guard that blocks agents evading denials via tool switching.", "readme_summary": "IntentFence cybersecurity copilot compares stateless policy vs objective-aware guard for denied sensitive ops. Detects replanning across tools, views or delegation. Prototype hosted as Vercel demo with docs and API.", "tech_highlights": [ "IntentFence Guard", "Policy Evasion Detect", "Vercel + Python API" ], "created_at": "2026-10-17T18:14:51Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 10, "commits_before_window": 13, "prs_total": 0, "prs_merged": 0, "is_preexisting": true, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": true, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": true, "live_urls": [ "https://agent-workflow-security.vercel.app" ], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.3, "score_meta_tooling": 0.5, "score_tech_depth": 1.0, "score_demo": 1.0, "score_total": 4.8, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "High-impact domain", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "5+ window commits (10)", "+0.2" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Automated CI workflow", "+0.2" ], [ "Pre-Oct 26 commits dominate (13)", "-0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Live web deployment", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 575, "is_new": true, "commits_delta": 10, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "rahulrao85/parda", "html_url": "https://github.com/rahulrao85/parda", "track": "Build for Your World", "domain": "Multimodal Vision & Video (SAM / Vision)", "summary": "Privacy filter that masks on-screen secrets and bleeps spoken PII in videos.", "readme_summary": "Parda detects private text, windows and speech in screen recordings and talking-head clips, then masks, bleeps and re-renders a clean MP4 with audit.json. Pipeline uses tracking masks plus approve UI with a verify agent recheck. Private mode runs detection on Meta open weights to avoid sending footage to closed APIs.", "tech_highlights": [ "Vision PII Detection", "Audio Redaction", "Muse Verify Agent" ], "created_at": "2026-10-28T16:22:50Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 9, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": true, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": true, "has_eval_benchmarks": false, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.3, "score_meta_tooling": 2.3, "score_tech_depth": 0.8, "score_demo": 0.4, "score_total": 4.8, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ], [ "Open-weights / fine-tuning", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "5+ window commits (9)", "+0.2" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ] ] }, "rank": 576, "is_new": false, "commits_delta": 2, "rank_delta": -250, "commits_delta_last_run": 0 }, { "full_name": "DanielSensual/guestlist", "html_url": "https://github.com/DanielSensual/guestlist", "track": "Build for Your World", "domain": "Multimodal Vision & Video (SAM / Vision)", "summary": "Event video system tracking every guest and building opt-out recaps", "readme_summary": "SAM 3.1 tracks every person across clips, Muse Spark selects moments and proposes roster matches for human confirm. Consent engine re-cuts recaps around opt-outs. Web app plus GhostCut pipeline for beat-sync cutting and FCPXML export.", "tech_highlights": [ "SAM 3.1 Vision", "Muse Spark", "GhostCut Pipeline" ], "created_at": "2026-10-26T21:13:43Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 7, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.3, "score_meta_tooling": 1.6, "score_tech_depth": 1.1, "score_demo": 0.8, "score_total": 4.8, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "5+ window commits (7)", "+0.2" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ] ] }, "rank": 577, "is_new": false, "commits_delta": 0, "rank_delta": -350, "commits_delta_last_run": 0 }, { "full_name": "carloux89/governed-agent-bridge", "html_url": "https://github.com/carloux89/governed-agent-bridge", "track": "Push the Frontier", "domain": "Autonomous Agents & Workflow Automation", "summary": "Governed desktop agent bridge with approval queue and audit log", "readme_summary": "Lets an AI agent work on user PC via Muse Spark JSON plans with read-auto and sensitive-approval classification. Executor runs only allowed actions, records hash-chained audit log with viewer. Synthetic demo data and installer included.", "tech_highlights": [ "Muse Spark Planner", "Approval + Audit Chain", "Desktop Executor" ], "created_at": "2026-10-26T22:14:45Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 6, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": false, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 1, "score_impact": 2.3, "score_meta_tooling": 1.3, "score_tech_depth": 0.8, "score_demo": 0.4, "score_total": 4.8, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "High-impact domain", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "5+ window commits (6)", "+0.2" ], [ "Automated test suite", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ] ] }, "rank": 578, "is_new": false, "commits_delta": 0, "rank_delta": -357, "commits_delta_last_run": 0 }, { "full_name": "parabellumlux/tidyquest", "html_url": "https://github.com/parabellumlux/tidyquest", "track": "Build for Your World", "domain": "Multimodal Vision & Video (SAM / Vision)", "summary": "Snaps a messy room photo to create energy-sized tidying quests verified by re-scan", "readme_summary": "Turns one photo of a messy space into a quest chain sized to user energy level. Uses a Python pipeline with schemas and validation where Muse Spark plans zones, boss battles and mystery-box steps, and photo diffing proves progress.", "tech_highlights": [ "Muse Spark", "Vision Photo Diffing", "Python Pipeline" ], "created_at": "2026-10-26T18:48:48Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 4, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": true, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.6, "score_meta_tooling": 1.8, "score_tech_depth": 0.6, "score_demo": 0.8, "score_total": 4.8, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ] ], "tech": [ [ "Base", "+0.3" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ] ] }, "rank": 579, "is_new": false, "commits_delta": 0, "rank_delta": -332, "commits_delta_last_run": 0 }, { "full_name": "anhafdev/Krishok-Bondhu", "html_url": "https://github.com/anhafdev/Krishok-Bondhu", "track": "Build for Your World", "domain": "Healthcare, Civic Tech & Sustainability", "summary": "Field agent for rice disease segmentation and micro-dosage guidance", "readme_summary": "Krishok-Bondhu helps Bangladeshi smallholders with spatial crop pathology and agronomic reasoning. It uses SAM 3.1 for leaf and lesion segmentation plus Muse Spark 1.3 and Glimmer 30B for IRRI-scale dosing, weather and inventory.", "tech_highlights": [ "SAM 3.1 Vision", "Muse Spark 1.3", "Muse Glimmer 30B" ], "created_at": "2026-10-30T10:00:22Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 3, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": true, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": true, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.6, "score_meta_tooling": 1.8, "score_tech_depth": 0.6, "score_demo": 0.8, "score_total": 4.8, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "High-impact domain", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ] ], "meta": [ [ "Base", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ], [ "Open-weights / fine-tuning", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ] ] }, "rank": 580, "is_new": false, "commits_delta": 0, "rank_delta": -427, "commits_delta_last_run": 0 }, { "full_name": "maikunari/physics-twin", "html_url": "https://github.com/maikunari/physics-twin", "track": "Push the Frontier", "domain": "Robotics, IoT & Manufacturing", "summary": "Turns phone video of ramp ball into fitted 2D physics simulation predictor", "readme_summary": "Converts 1s phone video of ball on ramp into 2D simulation, fitting friction and bounce to match footage to predict landing. Uses SAM 3.1 for tracking and Muse Spark for grounding and fitting via Meta Model API.", "tech_highlights": [ "SAM 3.1 Tracking", "Muse Spark", "Vite + Physics Sim" ], "created_at": "2026-10-27T13:04:45Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 3, "commits_before_window": 0, "prs_total": 2, "prs_merged": 2, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": true, "has_ci": true, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.0, "score_meta_tooling": 1.6, "score_tech_depth": 0.8, "score_demo": 0.4, "score_total": 4.8, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "High-impact domain", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Automated CI workflow", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ] ] }, "rank": 581, "is_new": false, "commits_delta": 0, "rank_delta": -348, "commits_delta_last_run": 0 }, { "full_name": "vherediadepvops/prooflab-ai-meta-hackathon-2026", "html_url": "https://github.com/vherediadepvops/prooflab-ai-meta-hackathon-2026", "track": "Push the Frontier", "domain": "Education & Knowledge Systems", "summary": "Scientific evidence engine that tests hypotheses against physical measurements", "readme_summary": "Experimental engine for researchers that makes testable predictions from measurements and explains agreement with hypotheses. Uses Meta models with offline calculations; SAM parsing and inference not yet verified.", "tech_highlights": [ "Meta Model API", "SAM Frame Parsing", ".NET + Lean" ], "created_at": "2026-10-26T16:59:02Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 3, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": true, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.2, "score_meta_tooling": 1.1, "score_tech_depth": 1.1, "score_demo": 0.4, "score_total": 4.8, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "Domain alignment", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Automated CI workflow", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ] ] }, "rank": 582, "is_new": false, "commits_delta": 0, "rank_delta": -378, "commits_delta_last_run": 0 }, { "full_name": "compiler-aditya/kepler", "html_url": "https://github.com/compiler-aditya/kepler", "track": "Build for Your World", "domain": "Multimodal Vision & Video (SAM / Vision)", "summary": "Turns phone video of motion into verified physics simulation data", "readme_summary": "Phone clip in, metric trajectory out checked against gravity. Pipeline uses SAM 3.1 ball tracking plus A4 homography for metres, outputting trajectory.json for theory agent, with 14 tests.", "tech_highlights": [ "SAM 3.1 Tracking", "Homography + Physics", "Python + Tests" ], "created_at": "2026-10-28T18:38:59Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 2, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.6, "score_meta_tooling": 1.3, "score_tech_depth": 0.9, "score_demo": 1.0, "score_total": 4.8, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 583, "is_new": false, "commits_delta": 0, "rank_delta": -285, "commits_delta_last_run": 0 }, { "full_name": "rajakumaranaap-rgb/makkal-ai", "html_url": "https://github.com/rajakumaranaap-rgb/makkal-ai", "track": "Build for Your World", "domain": "Healthcare, Civic Tech & Sustainability", "summary": "Tamil e-governance assistant bridging digital divide for 75M citizens", "readme_summary": "Helps Tamil Nadu citizens access e-Sevai services via conversational AI in Tamil and English. Python app with knowledge_base and meta_client using Meta Muse and SAM 2 for citizen queries.", "tech_highlights": [ "Muse Models", "SAM 2", "Python + Knowledge Base" ], "created_at": "2026-10-26T14:31:32Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 2, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": false, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.7, "score_meta_tooling": 1.8, "score_tech_depth": 0.3, "score_demo": 1.0, "score_total": 4.8, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "High-impact domain", "+0.4" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ] ], "tech": [ [ "Base", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 584, "is_new": false, "commits_delta": 0, "rank_delta": -333, "commits_delta_last_run": 0 }, { "full_name": "Octaves0911/meta-ai-hackathon", "html_url": "https://github.com/Octaves0911/meta-ai-hackathon", "track": "Build for Your World", "domain": "Business, Sales & Commerce", "summary": "Video meetings with live captions, memory, and agents that complete tasks", "readme_summary": "Monorepo with web, backend, connector, and FastAPI AI service plus Postgres pgvector memory. Spots decisions and answers @ai from history. Uses LLM keys and Deepgram for captions and project memory QA.", "tech_highlights": [ "FastAPI + Next.js", "pgvector Memory", "Deepgram Captions" ], "created_at": "2026-10-29T19:48:15Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 130, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": true, "has_ci": true, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.8, "score_meta_tooling": 0.5, "score_tech_depth": 1.4, "score_demo": 1.0, "score_total": 4.7, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (130)", "+0.6" ], [ "Modular src/ architecture", "+0.3" ], [ "Automated CI workflow", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 585, "is_new": true, "commits_delta": 130, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "valormarc/whatsapp-sales-agent", "html_url": "https://github.com/valormarc/whatsapp-sales-agent", "track": "Build for Your World", "domain": "Business, Sales & Commerce", "summary": "Small shop storefront, haggling, payments and books on WhatsApp", "readme_summary": "Go service on one shared WhatsApp number handles catalog, negotiation, MoMo payments and delivery. Keeps daily records for merchants with no dashboard or app to install.", "tech_highlights": [ "WhatsApp Business API", "Go Service", "MoMo Payments" ], "created_at": "2026-10-26T19:42:53Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 119, "commits_before_window": 0, "prs_total": 1, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": true, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.6, "score_meta_tooling": 1.3, "score_tech_depth": 1.2, "score_demo": 0.6, "score_total": 4.7, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (119)", "+0.6" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 586, "is_new": false, "commits_delta": 68, "rank_delta": -347, "commits_delta_last_run": 1 }, { "full_name": "arinafoodshq/prospect-research", "html_url": "https://github.com/arinafoodshq/prospect-research", "track": "Build for Your World", "domain": "Business, Sales & Commerce", "summary": "Prospecting agent that ranks leads with evidence and drafts outreach for approval", "readme_summary": "Agent takes business profile, plans searches, investigates public pages and drafts outreach held for human approval. Stack is Cloudflare Worker + D1 + Workflows. Uses muse-spark-1.3 for planning, research and drafting.", "tech_highlights": [ "Muse Spark 1.3", "Cloudflare Workers+D1", "Cloudflare Workflows" ], "created_at": "2026-10-29T06:04:36Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 93, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": false, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": true, "live_urls": [ "https://prospect-research.sam-5b1.workers.dev" ], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.5, "score_meta_tooling": 0.8, "score_tech_depth": 1.2, "score_demo": 1.2, "score_total": 4.7, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ] ], "meta": [ [ "Base", "+0.5" ], [ "Muse Spark integration", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (93)", "+0.6" ], [ "Automated test suite", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Live web deployment", "+0.4" ] ] }, "rank": 587, "is_new": false, "commits_delta": 85, "rank_delta": -239, "commits_delta_last_run": 2 }, { "full_name": "JaylyDev/ChromaInvert", "html_url": "https://github.com/JaylyDev/ChromaInvert", "track": "Build for Your World", "domain": "Multimodal Vision & Video (SAM / Vision)", "summary": "Recovers a smooth 3D LUT to match footage to a reference grade", "readme_summary": "Python differentiable color engine that optimizes a 3D LUT and exports portable .cube. C++ host with FFmpeg pipeline for preview and validation. Built with Meta proprietary and open-weights models for grade matching.", "tech_highlights": [ "3D LUT Engine", "Python + C++ FFmpeg", "Meta Models" ], "created_at": "2026-10-26T23:25:16Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 61, "commits_before_window": 0, "prs_total": 12, "prs_merged": 12, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": true, "has_ci": true, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": true, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.6, "score_meta_tooling": 0.5, "score_tech_depth": 1.8, "score_demo": 0.8, "score_total": 4.7, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Eval & benchmark proof", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (61)", "+0.6" ], [ "Modular src/ architecture", "+0.3" ], [ "Agent / eval harness", "+0.2" ], [ "Automated CI workflow", "+0.2" ], [ "PR review workflow (12 PRs)", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ] ] }, "rank": 588, "is_new": true, "commits_delta": 61, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "phsuroviec/gravit", "html_url": "https://github.com/phsuroviec/gravit", "track": "Build for Your World", "domain": "Gaming, Entertainment & Creative Media", "summary": "3D puzzle game where gravity follows foldable space regions you carry and place", "readme_summary": "Single-room Godot 4.7 puzzle built around FoldScope.applied_gravity. Player picks up inert folds and places them live to redirect falling. Uses online AI for airlock narration with local log fallback.", "tech_highlights": [ "Godot 4.7", "Custom Gravity System", "AI Narration" ], "created_at": "2026-10-26T17:38:27Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 56, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": true, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": true, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.4, "score_meta_tooling": 1.3, "score_tech_depth": 1.2, "score_demo": 0.8, "score_total": 4.7, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "General domain", "+0.2" ], [ "Multi-module scope (>10 files)", "+0.2" ] ], "meta": [ [ "Base", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "Open-weights / fine-tuning", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (56)", "+0.6" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ] ] }, "rank": 589, "is_new": false, "commits_delta": 3, "rank_delta": -255, "commits_delta_last_run": 0 }, { "full_name": "patelsaureen/clarity-room-meta-hackathon", "html_url": "https://github.com/patelsaureen/clarity-room-meta-hackathon", "track": "Build for Your World", "domain": "General & Emerging Applications", "summary": "Turns tough decisions into testable small experiments with grounded briefs.", "readme_summary": "Extracts facts, assumptions and trade-offs from a decision description with exact source quotes, then proposes reversible experiments. Next.js prototype with editable review flow. Uses Muse Spark 1.3 via Meta Model API as Extractor and Challenger.", "tech_highlights": [ "Muse Spark 1.3", "Next.js + Vercel", "Quote Grounding" ], "created_at": "2026-10-27T01:32:18Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 43, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": true, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": true, "live_urls": [ "https://clarity-room-meta-hackathon.vercel.app" ], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.2, "score_meta_tooling": 1.3, "score_tech_depth": 1.0, "score_demo": 1.2, "score_total": 4.7, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "General domain", "+0.2" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (43)", "+0.4" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Live web deployment", "+0.4" ] ] }, "rank": 590, "is_new": false, "commits_delta": 7, "rank_delta": -198, "commits_delta_last_run": 0 }, { "full_name": "mgoblimar/Ephemera", "html_url": "https://github.com/mgoblimar/Ephemera", "track": "Build for Your World", "domain": "Gaming, Entertainment & Creative Media", "summary": "Scans keepsakes and composes digital junk journal pages with AI", "readme_summary": "Mobile junk journaling app that scans tickets and stickers, cuts pieces with SAM 3.1 preserving torn edges, and composes themed pages. Muse Spark detects pieces, reads text/dates, and co-designs layouts. Proxy + app architecture per SPEC.md.", "tech_highlights": [ "SAM 3.1 Vision", "Muse Spark 1.3", "Mobile Journal App" ], "created_at": "2026-10-26T16:26:56Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 38, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.2, "score_meta_tooling": 1.8, "score_tech_depth": 1.3, "score_demo": 0.4, "score_total": 4.7, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "General domain", "+0.2" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (38)", "+0.4" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ] ] }, "rank": 591, "is_new": false, "commits_delta": 38, "rank_delta": -82, "commits_delta_last_run": 0 }, { "full_name": "Mvdodiya001/Meta-global-ai-developer-hackathon", "html_url": "https://github.com/Mvdodiya001/Meta-global-ai-developer-hackathon", "track": "Push the Frontier", "domain": "Legal & Compliance", "summary": "Version-aware verification tracing contract clauses to sources across revisions", "readme_summary": "ClauseTrace verifies contract clauses with version-aware legal checks. Backend is FastAPI Python 3.12 with SQLite, frontend React 18 Vite TypeScript Tailwind. Replay-mode demo API with LLM integration.", "tech_highlights": [ "FastAPI + React", "Legal Verification", "SQLite Replay API" ], "created_at": "2026-10-27T06:28:09Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 19, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": true, "has_ci": true, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.9, "score_meta_tooling": 0.8, "score_tech_depth": 1.2, "score_demo": 0.8, "score_total": 4.7, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "Domain alignment", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ] ], "meta": [ [ "Base", "+0.5" ], [ "Muse Spark integration", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (19)", "+0.4" ], [ "Modular src/ architecture", "+0.3" ], [ "Automated CI workflow", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ] ] }, "rank": 592, "is_new": false, "commits_delta": 12, "rank_delta": -230, "commits_delta_last_run": 2 }, { "full_name": "Angry-TacoZ/forrest-ai", "html_url": "https://github.com/Angry-TacoZ/forrest-ai", "track": "Build for Your World", "domain": "Business, Sales & Commerce", "summary": "Consented interview assistant that speaks only verified experience.", "readme_summary": "Planned flow: approved sources, speech transcription, retrieval, grounded draft, verification, candidate review, synthetic voice. Repo is bootstrap with AGENTS.md only, no implementation. Meta AI integration not yet implemented.", "tech_highlights": [ "RAG + Verification", "Speech Transcription", "Synthetic Voice" ], "created_at": "2026-10-28T04:55:43Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 18, "commits_before_window": 0, "prs_total": 1, "prs_merged": 1, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": true, "has_ci": true, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": true, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.6, "score_meta_tooling": 1.3, "score_tech_depth": 1.4, "score_demo": 0.4, "score_total": 4.7, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Eval & benchmark proof", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (18)", "+0.4" ], [ "Modular src/ architecture", "+0.3" ], [ "Agent / eval harness", "+0.2" ], [ "Automated CI workflow", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ] ] }, "rank": 593, "is_new": false, "commits_delta": 17, "rank_delta": -147, "commits_delta_last_run": 0 }, { "full_name": "labaccessnow/pausebird", "html_url": "https://github.com/labaccessnow/pausebird", "track": "Build for Your World", "domain": "Healthcare, Civic Tech & Sustainability", "summary": "Flags scam messages and fake checks to protect older parents, alerts family", "readme_summary": "Scam Shield reads screenshots and transcribes voicemails in Korean and English, checks links safely and verifies checks against writing. Built for Build for Your World track. Python fraudshield package with demo, tools and tests.", "tech_highlights": [ "Muse Spark", "Muse Voice Transcribe", "Scam Detection" ], "created_at": "2026-10-29T15:15:30Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 17, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": false, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.7, "score_meta_tooling": 1.6, "score_tech_depth": 1.0, "score_demo": 0.4, "score_total": 4.7, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "High-impact domain", "+0.4" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (17)", "+0.4" ], [ "Automated test suite", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ] ] }, "rank": 594, "is_new": true, "commits_delta": 17, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "barnikbh/brahma", "html_url": "https://github.com/barnikbh/brahma", "track": "Build for Your World", "domain": "Healthcare, Civic Tech & Sustainability", "summary": "Clinical decision support graph that shows only cited lines for synthetic cases", "readme_summary": "Walks synthetic cases through a cited clinical knowledge graph for decision support, not diagnosis. Local Python backend with web UI; uses Meta Model API with recorded-provider replay for tests.", "tech_highlights": [ "Meta Model API", "Knowledge Graph", "Python Backend" ], "created_at": "2026-10-31T05:11:38Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 9, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": true, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.6, "score_meta_tooling": 1.0, "score_tech_depth": 1.3, "score_demo": 0.8, "score_total": 4.7, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "High-impact domain", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "5+ window commits (9)", "+0.2" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Automated CI workflow", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ] ] }, "rank": 595, "is_new": true, "commits_delta": 9, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "caelum0x/menivor-meta-hackathon", "html_url": "https://github.com/caelum0x/menivor-meta-hackathon", "track": "Build for Your World", "domain": "Business, Sales & Commerce", "summary": "Video-ad generator wiring Meta image and segmentation into ad pipeline", "readme_summary": "Runnable extraction of Menivor production platform adding Meta Model API adapters. Includes Muse Image adapter for generations/edits and SAM 3.1 adapter for segmentation via responses API. Plugs into existing provider-routing architecture with tests.", "tech_highlights": [ "Muse Image", "SAM 3.1 Vision", "Python Routing" ], "created_at": "2026-10-26T19:48:17Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 7, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.3, "score_meta_tooling": 1.5, "score_tech_depth": 1.1, "score_demo": 0.8, "score_total": 4.7, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ] ], "tech": [ [ "Base", "+0.3" ], [ "5+ window commits (7)", "+0.2" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ] ] }, "rank": 596, "is_new": false, "commits_delta": 0, "rank_delta": -318, "commits_delta_last_run": 0 }, { "full_name": "rahulthms-art/VariantCut", "html_url": "https://github.com/rahulthms-art/VariantCut", "track": "Build for Your World", "domain": "Business, Sales & Commerce", "summary": "Agent team tells carmakers which variants to drop using only public EU data", "readme_summary": "Team of Muse Spark agents pulls public data into a database, runs backtests to 2022 and live verdicts to 2025, and writes a board memo with demo site. Python src/, results, logs and handcheck CSV, all built during hackathon.", "tech_highlights": [ "Muse Spark Agents", "EU Open Data", "Backtest + Live Demo" ], "created_at": "2026-11-01T21:20:49Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 6, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": true, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": true, "live_urls": [ "https://rahulthms-art.github.io/VariantCut/", "https://rahulthms-art.github.io/VariantCut/#MF222A2", "https://rahulthms-art.github.io/VariantCut/#live" ], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.6, "score_meta_tooling": 1.3, "score_tech_depth": 0.8, "score_demo": 1.0, "score_total": 4.7, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "5+ window commits (6)", "+0.2" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Live web deployment", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 597, "is_new": true, "commits_delta": 6, "rank_delta": 0, "commits_delta_last_run": 3 }, { "full_name": "Vilakazi-Technologies/meeting-pro-meta-hackathon-2026", "html_url": "https://github.com/Vilakazi-Technologies/meeting-pro-meta-hackathon-2026", "track": "Build for Your World", "domain": "Voice, Speech & Audio AI", "summary": "Transcribes WhatsApp business calls into searchable speaker transcripts", "readme_summary": "Meeting Pro converts WhatsApp Business calls to speaker-separated transcripts via Meta server-side transcription. Built with Expo SDK 58, React Native and Supabase. Notes phones cannot record WhatsApp calls directly.", "tech_highlights": [ "WhatsApp Calling API", "Meta Transcription", "Expo + Supabase" ], "created_at": "2026-10-28T16:22:23Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 1, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": true, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.8, "score_meta_tooling": 1.3, "score_tech_depth": 0.6, "score_demo": 1.0, "score_total": 4.7, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 598, "is_new": false, "commits_delta": 0, "rank_delta": -391, "commits_delta_last_run": 0 }, { "full_name": "MarsPresLai/atelier-muse", "html_url": "https://github.com/MarsPresLai/atelier-muse", "track": "Build for Your World", "domain": "Education & Knowledge Systems", "summary": "Interactive painting studio that generates replayable technique demos", "readme_summary": "Learn-by-doing painting studio that turns technique requests into replayable demonstrations with practice feedback. Uses Meta Muse muse-spark-1.3 via Meta Model API for lesson generation. Node.js frontend and server.", "tech_highlights": [ "Muse Spark 1.3", "Node.js + TS", "Replayable Demos" ], "created_at": "2026-10-31T07:22:20Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 1, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": true, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.5, "score_meta_tooling": 1.3, "score_tech_depth": 1.1, "score_demo": 0.8, "score_total": 4.7, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Automated CI workflow", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ] ] }, "rank": 599, "is_new": true, "commits_delta": 1, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "sajjadbdai/grp-costing", "html_url": "https://github.com/sajjadbdai/grp-costing", "track": "Build for Your World", "domain": "Business, Sales & Commerce", "summary": "Turns drawings and descriptions into reviewable GRP fiberglass cost estimates", "readme_summary": "Browser app for GFPF fiberglass costing with Upload-Review-Calculate workflow. FastAPI backend does deterministic geometry and pricing, Muse interprets drawings and narrates. Runs in manual mode without MODEL_API_KEY.", "tech_highlights": [ "Muse Wonder 1.0", "FastAPI + Docker", "Deterministic Costing" ], "created_at": "2026-10-31T17:17:30Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 1, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": true, "has_tests": true, "has_src": true, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.7, "score_meta_tooling": 1.3, "score_tech_depth": 0.9, "score_demo": 0.8, "score_total": 4.7, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Docker packaging", "+0.4" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ] ] }, "rank": 600, "is_new": true, "commits_delta": 1, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "zeroflaw/rsmpl-git", "html_url": "https://github.com/zeroflaw/rsmpl-git", "track": "Push the Frontier", "domain": "Developer Tooling, Infra & Security", "summary": "Semantic patch language for token-efficient Rust code refactoring by agents", "readme_summary": "gitrs apply lowers RSmPL-Git semantic hunks to Git diffs via applyrs, diff compresses changes via diffrs. Rust crates with SPEC.md and AGENTS.md. Designed for agentic refactoring with less tokens.", "tech_highlights": [ "Rust + Git", "SmPL Patches", "Agentic Refactor" ], "created_at": "2026-10-26T16:24:40Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 688, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": false, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.3, "score_meta_tooling": 0.5, "score_tech_depth": 1.2, "score_demo": 0.6, "score_total": 4.6, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "High-impact domain", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (688)", "+0.6" ], [ "Automated test suite", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 601, "is_new": true, "commits_delta": 688, "rank_delta": 0, "commits_delta_last_run": 9 }, { "full_name": "meschinidino/repo-city", "html_url": "https://github.com/meschinidino/repo-city", "track": "Push the Frontier", "domain": "Developer Tooling, Infra & Security", "summary": "Renders repos as isometric city to dispatch and watch coding agents", "readme_summary": "Maps modules to islands and files to buildings, imports to bridges, with CRUD agent quests and plain-English reports. Client + server prototype architecture. Uses Meta AI / Muse models for agent orchestration.", "tech_highlights": [ "Muse Agent", "Isometric Map UI", "Client + Server" ], "created_at": "2026-10-26T20:03:11Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 103, "commits_before_window": 0, "prs_total": 21, "prs_merged": 18, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.0, "score_meta_tooling": 0.5, "score_tech_depth": 1.7, "score_demo": 0.4, "score_total": 4.6, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "High-impact domain", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ] ], "meta": [ [ "Base", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (103)", "+0.6" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "PR review workflow (18 PRs)", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ] ] }, "rank": 602, "is_new": false, "commits_delta": 20, "rank_delta": -317, "commits_delta_last_run": 0 }, { "full_name": "Gabyresina15/kinetix-os", "html_url": "https://github.com/Gabyresina15/kinetix-os", "track": "Build for Your World", "domain": "Business, Sales & Commerce", "summary": "Spatial ERP orchestrator that grounds SAM vision into field workflows", "readme_summary": "Backend core for spatial ERP that converts SAM masks to semantic zones and orchestrates field agents. Fastify SSE server with Zod schemas, node:vm sandbox and Muse Spark planning. Includes edge PII shield pattern.", "tech_highlights": [ "SAM Vision", "Muse Spark", "Fastify SSE" ], "created_at": "2026-10-26T23:56:49Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 70, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": true, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.3, "score_meta_tooling": 1.3, "score_tech_depth": 1.2, "score_demo": 0.8, "score_total": 4.6, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (70)", "+0.6" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ] ] }, "rank": 603, "is_new": false, "commits_delta": 3, "rank_delta": -347, "commits_delta_last_run": 0 }, { "full_name": "mira-takeda/tiny-learner", "html_url": "https://github.com/mira-takeda/tiny-learner", "track": "Push the Frontier", "domain": "General & Emerging Applications", "summary": "CPU-first modular learner testing skill reuse and continual learning", "readme_summary": "Compact research system explores learning, retention, and transfer on unseen task combinations with Meta-designed curriculum. CPU-first Python experiments with runs, prereg, and logs. Concept demos for robotics and inspection.", "tech_highlights": [ "CPU Continual Learning", "Modular Skills", "Python Research" ], "created_at": "2026-10-26T20:44:58Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 47, "commits_before_window": 0, "prs_total": 1, "prs_merged": 1, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": true, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": true, "live_urls": [ "https://mira-takeda.github.io/tiny-learner/" ], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.1, "score_meta_tooling": 0.5, "score_tech_depth": 1.0, "score_demo": 1.0, "score_total": 4.6, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "General domain", "+0.2" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (47)", "+0.4" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Live web deployment", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 604, "is_new": true, "commits_delta": 47, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "axiomnetworks/echovision", "html_url": "https://github.com/axiomnetworks/echovision", "track": "Build for Your World", "domain": "Multimodal Vision & Video (SAM / Vision)", "summary": "Watches sample clips with gated backend and accessible viewer", "readme_summary": "Python backend plus browser UI with ffmpeg clip handling and one-hour pilot on generated samples. Inference fails closed behind secrets and privacy gates. Uses Meta-hosted SAM 3.1 and Muse Spark.", "tech_highlights": [ "SAM 3.1", "Muse Spark", "Python Backend" ], "created_at": "2026-10-27T00:57:13Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 32, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": true, "has_ci": true, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": true, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 1, "score_impact": 1.6, "score_meta_tooling": 0.8, "score_tech_depth": 1.4, "score_demo": 0.8, "score_total": 4.6, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Eval & benchmark proof", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Muse Spark integration", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (32)", "+0.4" ], [ "Modular src/ architecture", "+0.3" ], [ "Agent / eval harness", "+0.2" ], [ "Automated CI workflow", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ] ] }, "rank": 605, "is_new": true, "commits_delta": 32, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "deshanFdo/Meta-Global-AI-Developer-Hackathon", "html_url": "https://github.com/deshanFdo/Meta-Global-AI-Developer-Hackathon", "track": "Build for Your World", "domain": "Multimodal Vision & Video (SAM / Vision)", "summary": "Turns floor-plan images into interactive 3D homes you can walk and remodel", "readme_summary": "BlueprintTo3D extracts walls, doors, rooms and roof as strict JSON with Muse Spark 1.3 and rebuilds in Three.js. Supports editing, first-person walk, SAM 3.1 symbol check, restyle and GLB/DXF export.", "tech_highlights": [ "Muse Spark 1.3", "SAM 3.1 Vision", "Three.js + Next.js" ], "created_at": "2026-10-26T13:10:33Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 26, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": true, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.5, "score_meta_tooling": 1.3, "score_tech_depth": 1.0, "score_demo": 0.8, "score_total": 4.6, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ] ], "meta": [ [ "Base", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (26)", "+0.4" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ] ] }, "rank": 606, "is_new": false, "commits_delta": 13, "rank_delta": -260, "commits_delta_last_run": 0 }, { "full_name": "big14way/wireproof", "html_url": "https://github.com/big14way/wireproof", "track": "Build for Your World", "domain": "Robotics, IoT & Manufacturing", "summary": "Hands-free copilot verifies home wiring safety before plastering", "readme_summary": "Helps electricians check cable type, sizing and protection then gives homeowners an in-wall cable map. Repo with probe, web and infra components. Uses Meta models for voice-guided checks and verification.", "tech_highlights": [ "Voice Copilot", "Muse Models", "IoT Probe + Web" ], "created_at": "2026-10-27T18:46:52Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 19, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": false, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": true, "has_eval_benchmarks": false, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.7, "score_meta_tooling": 1.8, "score_tech_depth": 0.7, "score_demo": 0.4, "score_total": 4.6, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "High-impact domain", "+0.4" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ], [ "Open-weights / fine-tuning", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (19)", "+0.4" ] ], "demo": [ [ "Base", "+0.4" ] ] }, "rank": 607, "is_new": false, "commits_delta": 1, "rank_delta": -306, "commits_delta_last_run": 0 }, { "full_name": "rynclick/Pahami", "html_url": "https://github.com/rynclick/Pahami", "track": "Build for Your World", "domain": "Legal & Compliance", "summary": "WhatsApp agent helping litigants understand summons and track hearing dates", "readme_summary": "WhatsApp AI for Indonesian court users without lawyers, explaining summons and verdicts, tracking deadlines and preparing documents. Built for Indie Developer Build for Your World theme during hackathon period.", "tech_highlights": [ "WhatsApp Agent", "Legal Doc AI", "Hearing Tracker" ], "created_at": "2026-10-26T12:53:44Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 4, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": false, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": true, "has_eval_benchmarks": false, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.6, "score_meta_tooling": 2.3, "score_tech_depth": 0.3, "score_demo": 0.4, "score_total": 4.6, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ], [ "Open-weights / fine-tuning", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ] ] }, "rank": 608, "is_new": false, "commits_delta": 1, "rank_delta": -314, "commits_delta_last_run": 0 }, { "full_name": "KEYUR141/Oral-lens", "html_url": "https://github.com/KEYUR141/Oral-lens", "track": "Build for Your World", "domain": "Healthcare, Civic Tech & Sustainability", "summary": "Oral cancer literature workspace that links claims to source passages", "readme_summary": "Oral-lens is a research review workspace to compare studies and export evidence briefs. Stack is Python backend plus React starter with Meta Muse client using muse-spark-1.3; evidence workflow and live model verification remain planned.", "tech_highlights": [ "Muse Spark 1.3", "Python + React", "RAG Evidence Review" ], "created_at": "2026-10-25T12:42:22Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 3, "commits_before_window": 1, "prs_total": 0, "prs_merged": 0, "is_preexisting": true, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": true, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.9, "score_meta_tooling": 0.8, "score_tech_depth": 1.1, "score_demo": 0.8, "score_total": 4.6, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "High-impact domain", "+0.4" ], [ "Eval & benchmark proof", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ] ], "meta": [ [ "Base", "+0.5" ], [ "Muse Spark integration", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Agent / eval harness", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ] ] }, "rank": 609, "is_new": false, "commits_delta": 1, "rank_delta": -235, "commits_delta_last_run": 0 }, { "full_name": "soilrist/muse-playtester", "html_url": "https://github.com/soilrist/muse-playtester", "track": "Build for Your World", "domain": "Gaming, Entertainment & Creative Media", "summary": "AI agent watches game screens, presses keys, and writes reproducible bug reports with screenshots.", "readme_summary": "PlayTester perceives screenshots with SAM 3.1 to locate player and objects, then Muse Spark 1.3 picks press, click, wait and report actions. Rule checks complement model reports for reproducible bugs with captures. Product code in src/, with loop-starter-kit process template and viewer.", "tech_highlights": [ "SAM 3.1 Vision", "Muse Spark 1.3", "Python Agent Loop" ], "created_at": "2026-10-28T06:12:02Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 109, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": true, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.4, "score_meta_tooling": 1.1, "score_tech_depth": 1.2, "score_demo": 0.8, "score_total": 4.5, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "General domain", "+0.2" ], [ "Multi-module scope (>10 files)", "+0.2" ] ], "meta": [ [ "Base", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (109)", "+0.6" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ] ] }, "rank": 610, "is_new": false, "commits_delta": 17, "rank_delta": -374, "commits_delta_last_run": 0 }, { "full_name": "Anthony-Sin/inkbench", "html_url": "https://github.com/Anthony-Sin/inkbench", "track": "Build for Your World", "domain": "Robotics, IoT & Manufacturing", "summary": "Turns plain words into CAD parts with real geometry checks", "readme_summary": "Agentic CAD that drafts parametric specs with muse-spark-1.3, builds geometry in isometric viewport, then verifies collision, stability, assembly order and clearance with real math, iterating on failure.", "tech_highlights": [ "Muse Spark 1.3", "Parametric CAD Engine", "Geometric Verification" ], "created_at": "2026-10-26T17:30:02Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 13, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": true, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.6, "score_meta_tooling": 1.3, "score_tech_depth": 0.8, "score_demo": 0.8, "score_total": 4.5, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "High-impact domain", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "5+ window commits (13)", "+0.2" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ] ] }, "rank": 611, "is_new": false, "commits_delta": 0, "rank_delta": -339, "commits_delta_last_run": 0 }, { "full_name": "Mukeshreddy3/phantom-inventory-hunter", "html_url": "https://github.com/Mukeshreddy3/phantom-inventory-hunter", "track": "Build for Your World", "domain": "Business, Sales & Commerce", "summary": "Explains ERP vs WMS inventory gaps and queues fixes for approval", "readme_summary": "Long-running agent for food manufacturing that reconciles synthetic ERP and WMS records, investigates drift causes, proposes fixes, and holds them in human approval queue. Dashboard demo with Python backend.", "tech_highlights": [ "Muse Spark Agent", "Python Analytics", "ERP-WMS Reconciler" ], "created_at": "2026-10-26T20:13:07Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 13, "commits_before_window": 6, "prs_total": 0, "prs_merged": 0, "is_preexisting": true, "has_docker": false, "has_tests": true, "has_src": false, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.6, "score_meta_tooling": 1.3, "score_tech_depth": 0.8, "score_demo": 0.8, "score_total": 4.5, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "5+ window commits (13)", "+0.2" ], [ "Automated test suite", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ] ] }, "rank": 612, "is_new": false, "commits_delta": 0, "rank_delta": -351, "commits_delta_last_run": 0 }, { "full_name": "SebastianMejia1203/Dalo", "html_url": "https://github.com/SebastianMejia1203/Dalo", "track": "Build for Your World", "domain": "Healthcare, Civic Tech & Sustainability", "summary": "Translates between Colombian sign language and Spanish with 3D avatar", "readme_summary": "Dalo offers Spanish-to-sign animation and camera-based sign-to-Spanish proposals. Prototype has 33 animated expressions and 11 recognizable signs. Web prototype with 3D avatar needs validation with LSC users.", "tech_highlights": [ "3D Avatar Animation", "Camera Sign Recognition", "Web Prototype" ], "created_at": "2026-10-26T17:03:36Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 10, "commits_before_window": 0, "prs_total": 4, "prs_merged": 4, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": false, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 1, "score_impact": 1.7, "score_meta_tooling": 1.1, "score_tech_depth": 0.7, "score_demo": 1.0, "score_total": 4.5, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "High-impact domain", "+0.4" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "5+ window commits (10)", "+0.2" ], [ "PR review workflow (4 PRs)", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 613, "is_new": true, "commits_delta": 10, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "AIVONIC/second-hand", "html_url": "https://github.com/AIVONIC/second-hand", "track": "Build for Your World", "domain": "Multimodal Vision & Video (SAM / Vision)", "summary": "Hands-free glasses coworker for technicians that sees parts and drafts reports", "readme_summary": "Second Hand streams Ray-Ban Meta camera via Wearables Device Access Toolkit to Android plus server backend. Answers hands-free, segments parts, and enforces safety. Uses Muse Spark for reasoning and SAM 3.1 for part segmentation.", "tech_highlights": [ "SAM 3.1 Vision", "Muse Spark 1.3", "Ray-Ban Wearables SDK" ], "created_at": "2026-10-26T16:23:45Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 10, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": true, "has_ci": true, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.3, "score_meta_tooling": 1.8, "score_tech_depth": 1.0, "score_demo": 0.4, "score_total": 4.5, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ] ], "tech": [ [ "Base", "+0.3" ], [ "5+ window commits (10)", "+0.2" ], [ "Modular src/ architecture", "+0.3" ], [ "Automated CI workflow", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ] ] }, "rank": 614, "is_new": false, "commits_delta": 4, "rank_delta": -368, "commits_delta_last_run": 0 }, { "full_name": "kshepherd0128-crypto/sproutcomm", "html_url": "https://github.com/kshepherd0128-crypto/sproutcomm", "track": "Build for Your World", "domain": "Education & Knowledge Systems", "summary": "Voice-first Head Start family engagement with home-language audio and records", "readme_summary": "SproutComm connects advocates and families via per-family links with multilingual messaging and voice replies. Node HTTP server with SQLite store and Meta proxy, no-framework client. Uses Meta API for translation, TTS/STT, and documentation.", "tech_highlights": [ "Muse Voice + TTS", "Node + SQLite", "Multilingual PWA" ], "created_at": "2026-10-30T16:44:10Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 10, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": true, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.6, "score_meta_tooling": 1.1, "score_tech_depth": 0.8, "score_demo": 1.0, "score_total": 4.5, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "5+ window commits (10)", "+0.2" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 615, "is_new": true, "commits_delta": 10, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "felixbennet/before-the-tape", "html_url": "https://github.com/felixbennet/before-the-tape", "track": "Build for Your World", "domain": "Business, Sales & Commerce", "summary": "Overhead phone camera verifies parcel contents against barcode scans.", "readme_summary": "BeforeTheTape watches a packing bench, tracks parcels and items in video and reconciles them with scan logs to keep dispute evidence. Built as TypeScript pnpm workspace with bench footage pipeline. Uses SAM 3.1 for tracking and Muse Spark 1.3 for packing reasoning and catalog matching.", "tech_highlights": [ "SAM 3.1 Vision", "Muse Spark 1.3", "TypeScript Vision App" ], "created_at": "2026-10-26T21:33:10Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 9, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": true, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.3, "score_meta_tooling": 1.6, "score_tech_depth": 0.8, "score_demo": 0.8, "score_total": 4.5, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "5+ window commits (9)", "+0.2" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ] ] }, "rank": 616, "is_new": false, "commits_delta": 5, "rank_delta": -309, "commits_delta_last_run": 0 }, { "full_name": "EonEmmanuel/meta-ai-hackathon", "html_url": "https://github.com/EonEmmanuel/meta-ai-hackathon", "track": "Build for Your World", "domain": "Healthcare, Civic Tech & Sustainability", "summary": "Verifies Cameroon survey plans to catch inflated land areas and boundary errors.", "readme_summary": "Autonomous cadastral verification for Cameroon plans de bornage against MINDCAF standards. Backend geodetic checks for area fraud, closures, UTM zone mix-ups with frontend and PDF certificates. Uses Meta AI for extraction and audit reasoning.", "tech_highlights": [ "Geodetic Verification", "UTM EPSG:32632/33", "WhatsApp Bot" ], "created_at": "2026-10-28T08:10:14Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 9, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.7, "score_meta_tooling": 1.1, "score_tech_depth": 1.1, "score_demo": 0.6, "score_total": 4.5, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "High-impact domain", "+0.4" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "5+ window commits (9)", "+0.2" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 617, "is_new": false, "commits_delta": 9, "rank_delta": -95, "commits_delta_last_run": 0 }, { "full_name": "EonEmmanuel/Cadastra", "html_url": "https://github.com/EonEmmanuel/Cadastra", "track": "Build for Your World", "domain": "Healthcare, Civic Tech & Sustainability", "summary": "Verifies Cameroon survey plans to catch inflated land areas and boundary errors.", "readme_summary": "Autonomous cadastral verification for Cameroon plans de bornage against MINDCAF standards. Backend geodetic checks for area fraud, closures, UTM zone mix-ups with frontend and PDF certificates. Uses Meta AI for extraction and audit reasoning.", "tech_highlights": [ "Geodetic Verification", "Bilingual PDF Audit", "WhatsApp Bot" ], "created_at": "2026-10-28T08:10:14Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 9, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.7, "score_meta_tooling": 1.1, "score_tech_depth": 1.1, "score_demo": 0.6, "score_total": 4.5, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "High-impact domain", "+0.4" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "5+ window commits (9)", "+0.2" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 618, "is_new": true, "commits_delta": 9, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "Kaushal1025/spatial-sense", "html_url": "https://github.com/Kaushal1025/spatial-sense", "track": "Build for Your World", "domain": "Multimodal Vision & Video (SAM / Vision)", "summary": "Live camera narrator that speaks nearby objects for blind users.", "readme_summary": "Live scene navigator streaming camera frames every 2s to a Modal server. Parallel SAM 3.1 queries per phrase return boxes, Muse Spark generates spoken guidance. Web client speaks instructions and lists detections.", "tech_highlights": [ "SAM 3.1 Vision", "Muse Spark", "Modal + Web Speech" ], "created_at": "2026-10-26T21:18:02Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 7, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": true, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.3, "score_meta_tooling": 1.6, "score_tech_depth": 0.8, "score_demo": 0.8, "score_total": 4.5, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "5+ window commits (7)", "+0.2" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ] ] }, "rank": 619, "is_new": false, "commits_delta": 4, "rank_delta": -248, "commits_delta_last_run": 2 }, { "full_name": "paul0610/traductor-meta-hackathon", "html_url": "https://github.com/paul0610/traductor-meta-hackathon", "track": "Build for Your World", "domain": "Voice, Speech & Audio AI", "summary": "OS-level Spanish-English interpreter for any video call via virtual microphone", "readme_summary": "Captures mic audio, transcribes with Muse Voice Transcribe and translates with Muse Spark, outputting English via virtual mic and Spanish subtitles. No call-app plugin needed; written from scratch on Meta models.", "tech_highlights": [ "Muse Voice Transcribe", "Muse Spark", "Virtual Mic Audio" ], "created_at": "2026-10-30T01:26:38Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 6, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.5, "score_meta_tooling": 1.1, "score_tech_depth": 1.1, "score_demo": 0.8, "score_total": 4.5, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ] ], "meta": [ [ "Base", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "5+ window commits (6)", "+0.2" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ] ] }, "rank": 620, "is_new": true, "commits_delta": 6, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "unrealskill/sellerchat-ai", "html_url": "https://github.com/unrealskill/sellerchat-ai", "track": "Build for Your World", "domain": "Business, Sales & Commerce", "summary": "Indonesian live-chat seller agent with real order tools and transfer checks", "readme_summary": "Answers stock, price and order status in Indonesian via real SQLite tools. Verifies transfer screenshots, transcribes buyer voice notes, and escalates low-confidence cases for human approval.", "tech_highlights": [ "Muse Chat Agent", "SQLite Order Tools", "Vision + Transcription" ], "created_at": "2026-10-27T09:45:30Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 3, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": true, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.3, "score_meta_tooling": 1.8, "score_tech_depth": 0.6, "score_demo": 0.8, "score_total": 4.5, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ] ], "tech": [ [ "Base", "+0.3" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ] ] }, "rank": 621, "is_new": false, "commits_delta": 1, "rank_delta": -311, "commits_delta_last_run": 0 }, { "full_name": "anthonyokeleke/swayops-profit-investigation", "html_url": "https://github.com/anthonyokeleke/swayops-profit-investigation", "track": "Build for Your World", "domain": "Business, Sales & Commerce", "summary": "Browser tool that investigates profit scenarios with cited evidence and confirmation checks.", "readme_summary": "Adds evidence-backed profit briefing and 7-scenario investigation UI with citation checks and recovery. Uses TypeScript client/server/shared packages with Tailwind on Node 20. Runs in deterministic fixture mode with no Meta calls by default, requiring confirmation before inference.", "tech_highlights": [ "TypeScript + Node 20", "Tailwind CSS UI", "Fixture-mode demo" ], "created_at": "2026-11-01T20:42:40Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 2, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.8, "score_meta_tooling": 0.8, "score_tech_depth": 0.9, "score_demo": 1.0, "score_total": 4.5, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Muse Spark integration", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 622, "is_new": true, "commits_delta": 2, "rank_delta": 0, "commits_delta_last_run": 1 }, { "full_name": "Volosity/z-games", "html_url": "https://github.com/Volosity/z-games", "track": "Build for Your World", "domain": "Gaming, Entertainment & Creative Media", "summary": "Accessible voice-narrated shell making classic Z-machine text adventures playable hands-free.", "readme_summary": "Plays untouched .z3/.z5/.z8/.zblorb files with bundled Figaro starter; narrates text with highlighting, voice/tap/type input, compass chips and fog map. Built during hackathon across core/server/web/services for eyes-closed completion.", "tech_highlights": [ "Voice + TTS", "Z-Machine Engine", "Web + Server" ], "created_at": "2026-10-27T16:03:47Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 1, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.7, "score_meta_tooling": 1.3, "score_tech_depth": 0.9, "score_demo": 0.6, "score_total": 4.5, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "General domain", "+0.2" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 623, "is_new": false, "commits_delta": 0, "rank_delta": -460, "commits_delta_last_run": 0 }, { "full_name": "saivineethkoduri/pipeline-guardian", "html_url": "https://github.com/saivineethkoduri/pipeline-guardian", "track": "Push the Frontier", "domain": "Developer Tooling, Infra & Security", "summary": "Read-only pipeline fixer that proposes repairs for human approval", "readme_summary": "Self-healing data pipeline agent for failed loads. All tool calls go through a read-only gateway enforcing propose-only access against prompt injection. Currently design docs; code lands during build period.", "tech_highlights": [ "Read-only Gateway", "Log Analysis Agent", "Human-in-loop" ], "created_at": "2026-10-26T16:33:30Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 1, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": false, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": true, "has_eval_benchmarks": false, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.8, "score_meta_tooling": 2.0, "score_tech_depth": 0.3, "score_demo": 0.4, "score_total": 4.5, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "High-impact domain", "+0.4" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ], [ "Open-weights / fine-tuning", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ] ] }, "rank": 624, "is_new": false, "commits_delta": 0, "rank_delta": -294, "commits_delta_last_run": 0 }, { "full_name": "Teddy41682/coach", "html_url": "https://github.com/Teddy41682/coach", "track": "Build for Your World", "domain": "Multimodal Vision & Video (SAM / Vision)", "summary": "Hands-free cooking coach that watches via Ray-Ban Meta glasses", "readme_summary": "iOS app + worker backend watches camera stream from glasses/phone to guide cooking steps. Answers questions from observed video history, with recipe box and hands-free voice interaction.", "tech_highlights": [ "Ray-Ban Meta Glasses", "Live Video Coaching", "iOS + Worker" ], "created_at": "2026-10-27T20:43:56Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 101, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": false, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.6, "score_meta_tooling": 1.3, "score_tech_depth": 0.9, "score_demo": 0.6, "score_total": 4.4, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (101)", "+0.6" ] ], "demo": [ [ "Base", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 625, "is_new": false, "commits_delta": 36, "rank_delta": -387, "commits_delta_last_run": 0 }, { "full_name": "benjaminkwilliams/beyond-the-five-finger-problem", "html_url": "https://github.com/benjaminkwilliams/beyond-the-five-finger-problem", "track": "Push the Frontier", "domain": "Developer Tooling, Infra & Security", "summary": "Three-gate continuity checker for AI-generated frame sequences", "readme_summary": "Spike testing static validity, transition and spec compliance across frame pairs using named pixel sets. CPU-only Python with numpy, scipy, PIL on synthetic and real cases. Validates consistency across images, not inside one.", "tech_highlights": [ "NumPy + SciPy + PIL", "Validation Framework", "CPU-only Python" ], "created_at": "2026-10-14T04:15:59Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 86, "commits_before_window": 3, "prs_total": 0, "prs_merged": 0, "is_preexisting": true, "has_docker": false, "has_tests": true, "has_src": false, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.3, "score_meta_tooling": 0.5, "score_tech_depth": 1.2, "score_demo": 0.4, "score_total": 4.4, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "High-impact domain", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (86)", "+0.6" ], [ "Automated test suite", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ] ] }, "rank": 626, "is_new": true, "commits_delta": 86, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "Redaelm47/meta-motion-ads", "html_url": "https://github.com/Redaelm47/meta-motion-ads", "track": "Build for Your World", "domain": "Gaming, Entertainment & Creative Media", "summary": "Inserts freeze-frame motion ads into creator videos instead of mid-rolls.", "readme_summary": "Meta Motion Ads analyzes videos to find freeze moments and cut out subjects for ads. Pipeline with render, voice and cluster stages. Uses Muse Spark for moment selection, Muse Voice Transcribe and SAM 3.1.", "tech_highlights": [ "Muse Spark Video", "SAM 3.1 Vision", "Muse Voice Transcribe" ], "created_at": "2026-10-27T00:15:55Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 18, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": true, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": true, "has_eval_benchmarks": false, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.2, "score_meta_tooling": 1.8, "score_tech_depth": 1.0, "score_demo": 0.4, "score_total": 4.4, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "General domain", "+0.2" ] ], "meta": [ [ "Base", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ], [ "Open-weights / fine-tuning", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (18)", "+0.4" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ] ] }, "rank": 627, "is_new": false, "commits_delta": 0, "rank_delta": -304, "commits_delta_last_run": 0 }, { "full_name": "nsirivolu27/try-my-future-meta-hackathon", "html_url": "https://github.com/nsirivolu27/try-my-future-meta-hackathon", "track": "Build for Your World", "domain": "Education & Knowledge Systems", "summary": "Talking campus guide for prospective majors with tour planning and glasses support", "readme_summary": "Prototype searching 5,877 institutions with location-aware tour planning, notes and comparison. Stack is TypeScript, Android and server backend with Muse Spark Q&A and experimental Meta Gen 2 glasses integration.", "tech_highlights": [ "Muse Spark", "Android + Glasses", "TypeScript Server" ], "created_at": "2026-10-27T05:43:14Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 6, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": true, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.5, "score_meta_tooling": 0.8, "score_tech_depth": 1.3, "score_demo": 0.8, "score_total": 4.4, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ] ], "meta": [ [ "Base", "+0.5" ], [ "Muse Spark integration", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "5+ window commits (6)", "+0.2" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Automated CI workflow", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ] ] }, "rank": 628, "is_new": false, "commits_delta": 0, "rank_delta": -349, "commits_delta_last_run": 0 }, { "full_name": "Clean-earthw/tellmemore", "html_url": "https://github.com/Clean-earthw/tellmemore", "track": "Build for Your World", "domain": "Gaming, Entertainment & Creative Media", "summary": "Photographs heirlooms and records family voice stories into linked living pages", "readme_summary": "Family storytelling app where an object photo plus relative voice creates an explorable page with sentence-level attribution. Frontend plus backend with Supabase, built for Bringing People Closer Together track.", "tech_highlights": [ "Supabase Backend", "Voice Story Capture", "Next.js Frontend" ], "created_at": "2026-10-27T16:28:47Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 4, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": true, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.7, "score_meta_tooling": 1.1, "score_tech_depth": 0.6, "score_demo": 1.0, "score_total": 4.4, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "General domain", "+0.2" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 629, "is_new": false, "commits_delta": 0, "rank_delta": -346, "commits_delta_last_run": 0 }, { "full_name": "gino6178/meta_ai_hackathon", "html_url": "https://github.com/gino6178/meta_ai_hackathon", "track": "Build for Your World", "domain": "Autonomous Agents & Workflow Automation", "summary": "Sports club agent that schedules games, courts and health-aware plans", "readme_summary": "Serve agent lines up games with compatible players, negotiates via agents, plans around health data, books courts and cuts highlights. Runs on Muse Glimmer with Sapiens2, SAM 2.1 and DETR for video.", "tech_highlights": [ "Muse Glimmer", "SAM 2.1 + Sapiens2", "Agent Sports App" ], "created_at": "2026-10-27T03:33:08Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 4, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": true, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": true, "has_eval_benchmarks": false, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.7, "score_meta_tooling": 1.5, "score_tech_depth": 0.6, "score_demo": 0.6, "score_total": 4.4, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "High-impact domain", "+0.4" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Open-weights / fine-tuning", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 630, "is_new": false, "commits_delta": 0, "rank_delta": -337, "commits_delta_last_run": 0 }, { "full_name": "lukaesch/anypartmade-fixit", "html_url": "https://github.com/lukaesch/anypartmade-fixit", "track": "Build for Your World", "domain": "Robotics, IoT & Manufacturing", "summary": "Measures broken parts from a phone photo and designs 3D-printable replacements", "readme_summary": "Phone photo with coin reference enables SAM 3.1 measurement, Muse Spark knob-spec design loop, mesh to 3MF export. Verifies via Any Part Made MCP API for pricing. Rust plus Cloudflare Workers stack.", "tech_highlights": [ "SAM 3.1 Vision", "Muse Spark", "Rust + Workers" ], "created_at": "2026-10-31T22:45:03Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 3, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": true, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": true, "live_urls": [ "https://anypartmade-demo.jobboard.workers.dev" ], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.4, "score_meta_tooling": 1.6, "score_tech_depth": 0.6, "score_demo": 0.8, "score_total": 4.4, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "High-impact domain", "+0.4" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Live web deployment", "+0.4" ] ] }, "rank": 631, "is_new": true, "commits_delta": 3, "rank_delta": 0, "commits_delta_last_run": 1 }, { "full_name": "jscott3201/llm-tuning", "html_url": "https://github.com/jscott3201/llm-tuning", "track": "Push the Frontier", "domain": "Developer Tooling, Infra & Security", "summary": "Serves and fine-tunes Gemma, Qwen and Muse Glimmer models on Modal GPUs", "readme_summary": "Four self-contained projects for serving Gemma 4, Qwen and Muse Glimmer with SGLang and vLLM. Runs on Modal for solo and concurrent agentic-coding workloads with BYO-cloud support. Includes fine-tuning and speculative decoding setups.", "tech_highlights": [ "Muse Glimmer", "SGLang + vLLM", "Modal GPU Deploy" ], "created_at": "2026-06-08T15:33:11Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 2, "commits_before_window": 29, "prs_total": 13, "prs_merged": 13, "is_preexisting": true, "has_docker": false, "has_tests": true, "has_src": false, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": true, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 36, "score_impact": 2.1, "score_meta_tooling": 1.0, "score_tech_depth": 0.3, "score_demo": 1.0, "score_total": 4.4, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "High-impact domain", "+0.4" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Open-weights / fine-tuning", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "Automated test suite", "+0.3" ], [ "PR review workflow (13 PRs)", "+0.2" ], [ "Pre-existing repo (<=2 commits)", "-0.5" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 632, "is_new": true, "commits_delta": 2, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "luaartist/IPFS-hash_locker", "html_url": "https://github.com/luaartist/IPFS-hash_locker", "track": "Push the Frontier", "domain": "Developer Tooling, Infra & Security", "summary": "Encrypted container format with forensic validation and IPFS Filecoin ledger", "readme_summary": "Implements HLK v2 wire protocol with canonical CBOR, Zstandard compress-then-encrypt and AEAD ciphers. Uses Argon2id KDF and BLAKE3 with Python CLI plus Windows support. Provides forensic integrity validator and decentralized storage ledger, no Meta model dependency.", "tech_highlights": [ "AES-256-GCM-SIV", "Argon2id + BLAKE3", "IPFS/Filecoin" ], "created_at": "2026-10-31T02:21:52Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 1, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": true, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.0, "score_meta_tooling": 0.5, "score_tech_depth": 1.1, "score_demo": 0.8, "score_total": 4.4, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "High-impact domain", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ] ], "meta": [ [ "Base", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Automated CI workflow", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ] ] }, "rank": 633, "is_new": true, "commits_delta": 1, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "eswargutlapalli/refi_assist", "html_url": "https://github.com/eswargutlapalli/refi_assist", "track": "Build for Your World", "domain": "Finance, Crypto & Web3", "summary": "Compares mortgage refinance offers with verified math and explanations", "readme_summary": "Python tool to extract, compare and explain refinance offers with verification. Modules for engine, extract, explainer, verify and Streamlit app.py. Uses LLM via llm.py for explanations.", "tech_highlights": [ "Python + Streamlit", "Refinance Engine", "LLM Explainer" ], "created_at": "2026-10-28T05:56:39Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 43, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": false, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": true, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.8, "score_meta_tooling": 0.5, "score_tech_depth": 1.2, "score_demo": 0.8, "score_total": 4.3, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Eval & benchmark proof", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ] ], "meta": [ [ "Base", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (43)", "+0.4" ], [ "Automated test suite", "+0.3" ], [ "Agent / eval harness", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ] ] }, "rank": 634, "is_new": false, "commits_delta": 28, "rank_delta": -200, "commits_delta_last_run": 0 }, { "full_name": "finaspirant/lucky-passes", "html_url": "https://github.com/finaspirant/lucky-passes", "track": "Push the Frontier", "domain": "Developer Tooling, Infra & Security", "summary": "Tests if process-level scores select better coding-agent attempts than outcome signals", "readme_summary": "Research scaffold comparing process-level judges and calibration against outcome-only signals for picking coding-agent attempts. Python analysis pipeline with judges, calibration, and preregistered evaluation design.", "tech_highlights": [ "Python + pytest", "LLM Judges", "Calibration Analysis" ], "created_at": "2026-10-27T04:59:45Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 37, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": false, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.0, "score_meta_tooling": 0.5, "score_tech_depth": 1.0, "score_demo": 0.8, "score_total": 4.3, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "High-impact domain", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ] ], "meta": [ [ "Base", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (37)", "+0.4" ], [ "Automated test suite", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ] ] }, "rank": 635, "is_new": false, "commits_delta": 23, "rank_delta": -257, "commits_delta_last_run": 0 }, { "full_name": "manwithaneuralnetwork/dyad-meta-ai-hackathon", "html_url": "https://github.com/manwithaneuralnetwork/dyad-meta-ai-hackathon", "track": "Build for Your World", "domain": "General & Emerging Applications", "summary": "Activity-first social PWA that matches San Diego users by shared event interest", "readme_summary": "Next.js PWA recommending real events from onboarding preferences with Interested vs Find Company separation. Includes auth, activity catalog, AI-assisted tags, groups, invites and Realtime chat. Persists social data in Supabase with RLS.", "tech_highlights": [ "Next.js PWA", "Supabase + RLS", "Realtime Chat" ], "created_at": "2026-10-29T19:37:02Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 27, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.4, "score_meta_tooling": 0.8, "score_tech_depth": 1.3, "score_demo": 0.8, "score_total": 4.3, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "General domain", "+0.2" ], [ "Multi-module scope (>10 files)", "+0.2" ] ], "meta": [ [ "Base", "+0.5" ], [ "Muse Spark integration", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (27)", "+0.4" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ] ] }, "rank": 636, "is_new": true, "commits_delta": 27, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "0xmeowmeow/patchmate", "html_url": "https://github.com/0xmeowmeow/patchmate", "track": "Build for Your World", "domain": "General & Emerging Applications", "summary": "Double-blind introductions through shared questions, not profiles.", "readme_summary": "Patchmate matches people when both mark the same collaborative question, with opt-in sharing. Python backend with deploy scripts and tests. Built for live social field test with consent-off defaults.", "tech_highlights": [ "Python Backend", "Double-blind Matching", "Consent-first Design" ], "created_at": "2026-10-27T08:23:49Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 18, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.2, "score_meta_tooling": 1.0, "score_tech_depth": 1.3, "score_demo": 0.8, "score_total": 4.3, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "General domain", "+0.2" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (18)", "+0.4" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ] ] }, "rank": 637, "is_new": false, "commits_delta": 0, "rank_delta": -232, "commits_delta_last_run": 0 }, { "full_name": "Harpith2/25worlds", "html_url": "https://github.com/Harpith2/25worlds", "track": "Push the Frontier", "domain": "Robotics, IoT & Manufacturing", "summary": "Helps robots learn and navigate unseen spaces from one walkthrough", "readme_summary": "Builds spatial intelligence from a single camera walkthrough for robot navigation in unseen environments. Next.js/TypeScript app with cloud components focused on efficient physical AI.", "tech_highlights": [ "Spatial Intelligence", "Next.js + TypeScript", "Camera Walkthrough Map" ], "created_at": "2026-11-01T01:55:46Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 18, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": true, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.0, "score_meta_tooling": 0.5, "score_tech_depth": 1.0, "score_demo": 0.8, "score_total": 4.3, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "High-impact domain", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ] ], "meta": [ [ "Base", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (18)", "+0.4" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ] ] }, "rank": 638, "is_new": true, "commits_delta": 18, "rank_delta": 0, "commits_delta_last_run": 1 }, { "full_name": "rikuy-si/rikuy-meta-hackathon", "html_url": "https://github.com/rikuy-si/rikuy-meta-hackathon", "track": "Push the Frontier", "domain": "Developer Tooling, Infra & Security", "summary": "Local gateway that gives AI agents permissioned access to any camera", "readme_summary": "Plans local gateway for RTSP/ONVIF, Hikvision ISAPI and WebRTC with REST/MCP contract, grants, audit log and revocation. Intends Muse Spark as agent, SAM 3.1 for anonymization/search, Muse Spark Open on Baseten. Day 0, work in progress.", "tech_highlights": [ "Muse Spark Agent", "SAM 3.1 Anonymization", "REST + MCP Gateway" ], "created_at": "2026-10-26T16:54:25Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 2, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": false, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": true, "has_eval_benchmarks": false, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.8, "score_meta_tooling": 1.8, "score_tech_depth": 0.3, "score_demo": 0.4, "score_total": 4.3, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "High-impact domain", "+0.4" ] ], "meta": [ [ "Base", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ], [ "Open-weights / fine-tuning", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ] ] }, "rank": 639, "is_new": false, "commits_delta": 0, "rank_delta": -225, "commits_delta_last_run": 0 }, { "full_name": "an-cyberflux-sec/safe-house-vision", "html_url": "https://github.com/an-cyberflux-sec/safe-house-vision", "track": "Push the Frontier", "domain": "Developer Tooling, Infra & Security", "summary": "Local-first camera pipeline detecting events with graded alerts and evidence custody", "readme_summary": "Safe House turns existing cameras into detection to graded alert to tamper-evident evidence. Local detection filters video and only candidates go to Muse Spark Open via Baseten for verification. Verified alerts are sent to human via WhatsApp with measured egress and hashes.", "tech_highlights": [ "Muse Spark via Baseten", "Local-First Detection", "Tamper-Evident Evidence" ], "created_at": "2026-10-28T13:10:35Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 2, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": false, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": true, "has_eval_benchmarks": true, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.1, "score_meta_tooling": 1.3, "score_tech_depth": 0.5, "score_demo": 0.4, "score_total": 4.3, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "High-impact domain", "+0.4" ], [ "Eval & benchmark proof", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "Open-weights / fine-tuning", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "Agent / eval harness", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ] ] }, "rank": 640, "is_new": false, "commits_delta": 2, "rank_delta": -136, "commits_delta_last_run": 0 }, { "full_name": "josephbolus/daas-meta-demo-video", "html_url": "https://github.com/josephbolus/daas-meta-demo-video", "track": "Push the Frontier", "domain": "Developer Tooling, Infra & Security", "summary": "Programmatic Remotion video showcasing real DevOps as a Service console", "readme_summary": "2:45 1080p captioned demo built with Remotion replaying real v3 console captures. Uses actual Mock Judge Mode run, guardrail verdict and console rendering code, no mocked UI.", "tech_highlights": [ "Remotion Video", "DevOps Console Replay", "Guardrail Demo" ], "created_at": "2026-10-29T18:05:15Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 2, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": true, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.3, "score_meta_tooling": 0.8, "score_tech_depth": 0.6, "score_demo": 0.6, "score_total": 4.3, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "High-impact domain", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 641, "is_new": true, "commits_delta": 2, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "suhailps93/ayma-practice-date", "html_url": "https://github.com/suhailps93/ayma-practice-date", "track": "Build for Your World", "domain": "General & Emerging Applications", "summary": "AI practice-date simulator for a dating app with Meta model provider", "readme_summary": "Hackathon subset of Ayma with two deliverables. Adds a Meta Muse Spark and Muse Voice Transcribe provider behind a per-surface flag with Gemini fallback. Implements Practice Date conversational simulator; Flutter plus backend.", "tech_highlights": [ "Muse Spark", "Muse Voice Transcribe", "Flutter + Backend" ], "created_at": "2026-10-26T16:07:20Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 1, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": true, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.5, "score_meta_tooling": 1.6, "score_tech_depth": 0.6, "score_demo": 0.6, "score_total": 4.3, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "General domain", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 642, "is_new": false, "commits_delta": 0, "rank_delta": -467, "commits_delta_last_run": 0 }, { "full_name": "faridadamncoder/warungcopilot", "html_url": "https://github.com/faridadamncoder/warungcopilot", "track": "Build for Your World", "domain": "Business, Sales & Commerce", "summary": "WhatsApp sales assistant for Indonesian shops with QRIS checkout", "readme_summary": "AI sales assistant over WhatsApp for Indonesian UMKM. Reads live catalog, answers in everyday language, compares products and builds structured orders with QRIS payment links. Python src with demo script.", "tech_highlights": [ "WhatsApp Commerce", "Muse Spark", "QRIS + Catalog" ], "created_at": "2026-10-27T02:49:42Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 1, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.3, "score_meta_tooling": 1.3, "score_tech_depth": 0.9, "score_demo": 0.8, "score_total": 4.3, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ] ] }, "rank": 643, "is_new": false, "commits_delta": 0, "rank_delta": -332, "commits_delta_last_run": 0 }, { "full_name": "ngoldbla/cv-meta-hackathon-2026", "html_url": "https://github.com/ngoldbla/cv-meta-hackathon-2026", "track": "Build for Your World", "domain": "Healthcare, Civic Tech & Sustainability", "summary": "Agent loop co-designs emergency-logistics scenarios and response policies", "readme_summary": "Open research with frozen calibrated simulator and evaluator as judge. Blue loop optimizes response policies, red loop evolves worst-case scenarios, all iterations logged. Simulation-only, MIT code, CC BY data, MCP and datasets.", "tech_highlights": [ "Agent Autoresearch", "Calibrated Simulator", "Policy Optimization" ], "created_at": "2026-10-26T16:23:40Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 175, "commits_before_window": 0, "prs_total": 1, "prs_merged": 1, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": true, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.6, "score_meta_tooling": 0.5, "score_tech_depth": 1.7, "score_demo": 0.4, "score_total": 4.2, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "High-impact domain", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ] ], "meta": [ [ "Base", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (175)", "+0.6" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Automated CI workflow", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ] ] }, "rank": 644, "is_new": false, "commits_delta": 165, "rank_delta": -369, "commits_delta_last_run": 26 }, { "full_name": "xAtomizerx/void-terminal-studios", "html_url": "https://github.com/xAtomizerx/void-terminal-studios", "track": "Build for Your World", "domain": "Business, Sales & Commerce", "summary": "The Pass: recipes and daily prep manager for restaurant kitchens", "readme_summary": "Monorepo portfolio whose hackathon entry is The Pass at thepass.site. Manages recipes and daily kitchen prep. Built with Next.js frontend, FastAPI backend, shared Python packages and Cloudflare tunnel deploy.", "tech_highlights": [ "Muse Spark 1.3", "FastAPI + Next.js", "Monorepo CI" ], "created_at": "2026-10-30T18:32:34Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 96, "commits_before_window": 120, "prs_total": 0, "prs_merged": 0, "is_preexisting": true, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": true, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.5, "score_meta_tooling": 0.5, "score_tech_depth": 1.4, "score_demo": 0.8, "score_total": 4.2, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ] ], "meta": [ [ "Base", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (96)", "+0.6" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Automated CI workflow", "+0.2" ], [ "Pre-Oct 26 commits dominate (120)", "-0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ] ] }, "rank": 645, "is_new": true, "commits_delta": 96, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "hrodge107/JustMaya", "html_url": "https://github.com/hrodge107/JustMaya", "track": "Build for Your World", "domain": "General & Emerging Applications", "summary": "Web app prototype with React frontend and backend service scaffold", "readme_summary": "A hackathon entry with React TypeScript Vite frontend, backend folder and prototype assets. README is default Vite template so exact features are unclear from files. Uses web stack with build scripts and static public assets.", "tech_highlights": [ "React + Vite", "TypeScript", "Node.js Backend" ], "created_at": "2026-10-27T11:31:21Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 80, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.4, "score_meta_tooling": 0.5, "score_tech_depth": 1.5, "score_demo": 0.8, "score_total": 4.2, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "General domain", "+0.2" ], [ "Multi-module scope (>10 files)", "+0.2" ] ], "meta": [ [ "Base", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (80)", "+0.6" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ] ] }, "rank": 646, "is_new": false, "commits_delta": 54, "rank_delta": -328, "commits_delta_last_run": 0 }, { "full_name": "vikashsaravanann/groundline-hackathon-2026", "html_url": "https://github.com/vikashsaravanann/groundline-hackathon-2026", "track": "Build for Your World", "domain": "Autonomous Agents & Workflow Automation", "summary": "Turns product photo plus typed goal into reviewable structured assistance", "readme_summary": "Camera-consent still or upload plus typed objective produces structured reviewable fields. Human must approve; no auto submit or purchase. Mock-mode FastAPI backend with Next.js Studio frontend.", "tech_highlights": [ "Vision-to-Action AI", "FastAPI + Next.js", "Human-in-the-loop" ], "created_at": "2026-10-26T17:26:41Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 52, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": false, "has_ci": true, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": true, "live_urls": [ "https://groundline-hackathon-2026.vercel.app" ], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.4, "score_meta_tooling": 0.5, "score_tech_depth": 1.1, "score_demo": 1.2, "score_total": 4.2, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "High-impact domain", "+0.4" ] ], "meta": [ [ "Base", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (52)", "+0.6" ], [ "Automated CI workflow", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Live web deployment", "+0.4" ] ] }, "rank": 647, "is_new": false, "commits_delta": 0, "rank_delta": -270, "commits_delta_last_run": 0 }, { "full_name": "ghatoleaakruti/draftCheck", "html_url": "https://github.com/ghatoleaakruti/draftCheck", "track": "Build for Your World", "domain": "Robotics, IoT & Manufacturing", "summary": "Checks engineering drawings for dimensioning, GD&T and manufacturability errors.", "readme_summary": "Analyzes engineering drawings to flag dimensioning, GD&T and manufacturability issues. Python stack with samples, scripts and tests for drawing checks. Uses Meta AI vision-language models to interpret drawings and explain errors.", "tech_highlights": [ "Vision Drawing Check", "GD&T Rules Engine", "Python Agent" ], "created_at": "2026-10-28T00:00:00Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 45, "commits_before_window": 0, "prs_total": 21, "prs_merged": 21, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": true, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.6, "score_meta_tooling": 0.5, "score_tech_depth": 1.7, "score_demo": 0.4, "score_total": 4.2, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "High-impact domain", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ] ], "meta": [ [ "Base", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (45)", "+0.4" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Automated CI workflow", "+0.2" ], [ "PR review workflow (21 PRs)", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ] ] }, "rank": 648, "is_new": false, "commits_delta": 32, "rank_delta": -250, "commits_delta_last_run": 0 }, { "full_name": "lechador/nodesnap", "html_url": "https://github.com/lechador/nodesnap", "track": "Build for Your World", "domain": "Autonomous Agents & Workflow Automation", "summary": "Chat-driven home design workspace with traceable 3D model and review exports", "readme_summary": "Homeowner workspace built around an authoritative Python building model with studio, walls, stairs and dimensioned plans. FastAPI + Next.js with SQLite/Postgres and Docker Compose deploy. Uses Meta AI for conversational edits and revision-specific review drafts.", "tech_highlights": [ "Muse Spark", "FastAPI + Next.js", "SQLite / Postgres" ], "created_at": "2026-10-30T08:36:27Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 34, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.6, "score_meta_tooling": 0.5, "score_tech_depth": 1.3, "score_demo": 0.8, "score_total": 4.2, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "High-impact domain", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ] ], "meta": [ [ "Base", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (34)", "+0.4" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ] ] }, "rank": 649, "is_new": true, "commits_delta": 34, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "yethikrishna/meta-handoff-studio-2026", "html_url": "https://github.com/yethikrishna/meta-handoff-studio-2026", "track": "Push the Frontier", "domain": "Developer Tooling, Infra & Security", "summary": "Prototype for permission-aware agent delegation with explicit scope and audit trace", "readme_summary": "Event-period prototype making agent delegation scope explicit and blocking out-of-scope disclosures. Cloudflare Workers AI backend uses Meta Llama 3.2 1B Instruct binding with server-side validation. Browser sends synthetic prompts, no token in client.", "tech_highlights": [ "Llama 3.2 1B Instruct", "Cloudflare Workers AI", "Scoped Delegation" ], "created_at": "2026-10-26T23:02:05Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 25, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.0, "score_meta_tooling": 0.5, "score_tech_depth": 1.3, "score_demo": 0.4, "score_total": 4.2, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "High-impact domain", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ] ], "meta": [ [ "Base", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (25)", "+0.4" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ] ] }, "rank": 650, "is_new": false, "commits_delta": 0, "rank_delta": -331, "commits_delta_last_run": 0 }, { "full_name": "ekumahost/TraceX", "html_url": "https://github.com/ekumahost/TraceX", "track": "Build for Your World", "domain": "Finance, Crypto & Web3", "summary": "AI blockchain forensics tracing crypto flows into evidence briefs", "readme_summary": "Traces flows across 7 EVM chains with deterministic laundering detectors, then drafts evidence-backed briefs and recovery reports. Python detectors on Modal with web app frontend. Uses Meta Muse Spark citing transaction hash for every claim.", "tech_highlights": [ "Muse Spark", "Modal Detectors", "7-Chain Tracing" ], "created_at": "2026-10-27T10:34:46Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 24, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": false, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.6, "score_meta_tooling": 1.3, "score_tech_depth": 0.7, "score_demo": 0.6, "score_total": 4.2, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (24)", "+0.4" ] ], "demo": [ [ "Base", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 651, "is_new": false, "commits_delta": 7, "rank_delta": -380, "commits_delta_last_run": 0 }, { "full_name": "Taleyvital/DevisVocal", "html_url": "https://github.com/Taleyvital/DevisVocal", "track": "Build for Your World", "domain": "Business, Sales & Commerce", "summary": "WhatsApp voice-note to professional PDF quote assistant for artisans.", "readme_summary": "DevisVocal converts artisan voice notes into priced PDF quotes via WhatsApp. Built with Next.js, Supabase and TypeScript. Uses Meta Muse models for transcription and quote generation.", "tech_highlights": [ "Muse Models", "Next.js + Supabase", "WhatsApp Voice-to-PDF" ], "created_at": "2026-10-26T13:55:07Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 23, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": true, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": true, "live_urls": [ "https://devis-vocal-neon.vercel.app" ], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.5, "score_meta_tooling": 0.5, "score_tech_depth": 1.0, "score_demo": 1.2, "score_total": 4.2, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ] ], "meta": [ [ "Base", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (23)", "+0.4" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Live web deployment", "+0.4" ] ] }, "rank": 652, "is_new": false, "commits_delta": 5, "rank_delta": -293, "commits_delta_last_run": 0 }, { "full_name": "OpenxIntelligence/open-intelligence", "html_url": "https://github.com/OpenxIntelligence/open-intelligence", "track": "Build for Your World", "domain": "Healthcare, Civic Tech & Sustainability", "summary": "Oncology workspace linking patient records to inspectable evidence and questions", "readme_summary": "Open Intelligence is an AI-native oncology platform for longitudinal understanding of cancer with investigations tied to evidence. Current prototype is local Python/SQLite with synthetic data, case workspaces and versioned reports; clinical decisions stay with professionals.", "tech_highlights": [ "Python + SQLite", "Evidence-Grounded AI", "Clinical Workspaces" ], "created_at": "2026-10-31T13:56:26Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 23, "commits_before_window": 0, "prs_total": 34, "prs_merged": 17, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": true, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.6, "score_meta_tooling": 0.5, "score_tech_depth": 1.7, "score_demo": 0.4, "score_total": 4.2, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "High-impact domain", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ] ], "meta": [ [ "Base", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (23)", "+0.4" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Automated CI workflow", "+0.2" ], [ "PR review workflow (17 PRs)", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ] ] }, "rank": 653, "is_new": true, "commits_delta": 23, "rank_delta": 0, "commits_delta_last_run": 1 }, { "full_name": "JuanMontreuil08/confio", "html_url": "https://github.com/JuanMontreuil08/confio", "track": "Build for Your World", "domain": "Voice, Speech & Audio AI", "summary": "Button-activated Spanish voice assistant gadget for older adults without smartphones", "readme_summary": "Confio is a handheld ESP32 gadget with large buttons that lets older adults ask questions by voice in Spanish and hear spoken answers. It uses WiFi to a laptop backend plus web app, with Meta AI powering conversational assistance for daily needs.", "tech_highlights": [ "ESP32 + WiFi", "Spanish Voice AI", "Muse Spark" ], "created_at": "2026-10-29T03:30:13Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 21, "commits_before_window": 0, "prs_total": 5, "prs_merged": 5, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": true, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.5, "score_meta_tooling": 1.1, "score_tech_depth": 1.2, "score_demo": 0.4, "score_total": 4.2, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ] ], "meta": [ [ "Base", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (21)", "+0.4" ], [ "Modular src/ architecture", "+0.3" ], [ "PR review workflow (5 PRs)", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ] ] }, "rank": 654, "is_new": false, "commits_delta": 16, "rank_delta": -271, "commits_delta_last_run": 0 }, { "full_name": "jenksed/yourmove-hackathon", "html_url": "https://github.com/jenksed/yourmove-hackathon", "track": "Build for Your World", "domain": "Business, Sales & Commerce", "summary": "Local macOS app to track jobs, resumes and applications", "readme_summary": "Go desktop app with local workspace and browser-mode server on port 3019. Keeps opportunities, resumes, and submission records on-device in Apple Silicon bundle. Applicant reviews and submits manually.", "tech_highlights": [ "Go Desktop App", "Local-First macOS", "Job Workspace" ], "created_at": "2026-10-26T15:07:32Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 21, "commits_before_window": 135, "prs_total": 0, "prs_merged": 0, "is_preexisting": true, "has_docker": false, "has_tests": false, "has_src": true, "has_ci": true, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.8, "score_meta_tooling": 0.5, "score_tech_depth": 0.9, "score_demo": 1.0, "score_total": 4.2, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (21)", "+0.4" ], [ "Modular src/ architecture", "+0.3" ], [ "Automated CI workflow", "+0.2" ], [ "Pre-Oct 26 commits dominate (135)", "-0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 655, "is_new": true, "commits_delta": 21, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "itvboy/cidd", "html_url": "https://github.com/itvboy/cidd", "track": "Push the Frontier", "domain": "Developer Tooling, Infra & Security", "summary": "Deterministic engine that generates software via isolated contract-bound LLM workers", "readme_summary": "CIDD orchestrates software generation without autonomous agents using deterministic contracts. Isolated LLM workers receive bounded specs, return code, with no file access or planning. Controls process externally for scalable context.", "tech_highlights": [ "Contract Isolation", "Deterministic Orchestrator", "LLM Code Workers" ], "created_at": "2026-10-27T01:08:06Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 15, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 2, "score_impact": 2.0, "score_meta_tooling": 0.5, "score_tech_depth": 1.3, "score_demo": 0.4, "score_total": 4.2, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "High-impact domain", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ] ], "meta": [ [ "Base", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (15)", "+0.4" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ] ] }, "rank": 656, "is_new": true, "commits_delta": 15, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "hadxits/frontierbase-meta-hackathon", "html_url": "https://github.com/hadxits/frontierbase-meta-hackathon", "track": "Build for Your World", "domain": "Voice, Speech & Audio AI", "summary": "Turns support FAQs into tested voice menus that staff can review and repair", "readme_summary": "FrontierBase ARS converts spreadsheets and policy FAQs into voice menus, checks routes and repairs drafts before staff review. Stack is Vue 3 console, Vite widget, Node.js 22 and Firebase, using Meta Muse Spark 1.3 and ElevenLabs for voice.", "tech_highlights": [ "Muse Spark 1.3", "Vue 3 + Firebase", "ElevenLabs Voice" ], "created_at": "2026-10-26T06:47:06Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 13, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": false, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.8, "score_meta_tooling": 1.3, "score_tech_depth": 0.5, "score_demo": 0.6, "score_total": 4.2, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "5+ window commits (13)", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 657, "is_new": false, "commits_delta": 6, "rank_delta": -437, "commits_delta_last_run": 0 }, { "full_name": "Kazi16/suite-fleet", "html_url": "https://github.com/Kazi16/suite-fleet", "track": "Push the Frontier", "domain": "Autonomous Agents & Workflow Automation", "summary": "Personal agent fleet for mail, leads and notes with cost tracking", "readme_summary": "Working fleet on one server triaging mail, scoring leads and checking notes under approval gates. Hackathon rebuild swaps model layer to Meta models to measure cost, latency and verdicts with public dashboard.", "tech_highlights": [ "Muse Spark 1.3", "Agent Fleet Routing", "Latency/Cost Eval" ], "created_at": "2026-10-26T22:02:01Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 12, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": false, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": true, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.4, "score_meta_tooling": 0.5, "score_tech_depth": 0.7, "score_demo": 0.6, "score_total": 4.2, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "High-impact domain", "+0.4" ], [ "Eval & benchmark proof", "+0.3" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "5+ window commits (12)", "+0.2" ], [ "Agent / eval harness", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 658, "is_new": false, "commits_delta": 10, "rank_delta": -222, "commits_delta_last_run": 0 }, { "full_name": "andrewliang13/handoff", "html_url": "https://github.com/andrewliang13/handoff", "track": "Build for Your World", "domain": "Business, Sales & Commerce", "summary": "Turns leader exit interviews into cited day-one playbooks successors can query", "readme_summary": "Handoff converts voice/text exit interviews into a claim-cited playbook using transcript turns. Built with Next.js with sample Northline Labs fixtures and no API call for demo load. Uses Meta API to generate playbook and abstain on uncovered topics.", "tech_highlights": [ "Next.js + TypeScript", "Muse Text Models", "Grounded Q&A" ], "created_at": "2026-10-23T15:47:46Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 8, "commits_before_window": 1, "prs_total": 0, "prs_merged": 0, "is_preexisting": true, "has_docker": false, "has_tests": false, "has_src": true, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.5, "score_meta_tooling": 1.1, "score_tech_depth": 0.8, "score_demo": 0.8, "score_total": 4.2, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ] ], "meta": [ [ "Base", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "5+ window commits (8)", "+0.2" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ] ] }, "rank": 659, "is_new": false, "commits_delta": 0, "rank_delta": -355, "commits_delta_last_run": 0 }, { "full_name": "remtekindo/milestone-guardian", "html_url": "https://github.com/remtekindo/milestone-guardian", "track": "Build for Your World", "domain": "Finance, Crypto & Web3", "summary": "Milestone life planner that projects savings timelines with AI explanations", "readme_summary": "Households set milestones like wedding or home payment; deterministic engine projects dates from savings rate. Muse Spark via Meta Model API only explains numbers. Nuxt 4 + Drizzle standalone repo.", "tech_highlights": [ "Muse Spark", "Nuxt 4 + Vue", "Drizzle Projections" ], "created_at": "2026-10-27T15:50:26Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 3, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": true, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.5, "score_meta_tooling": 1.3, "score_tech_depth": 0.6, "score_demo": 0.8, "score_total": 4.2, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ] ] }, "rank": 660, "is_new": false, "commits_delta": 0, "rank_delta": -428, "commits_delta_last_run": 0 }, { "full_name": "jczdigitalproductions/Muse", "html_url": "https://github.com/jczdigitalproductions/Muse", "track": "Build for Your World", "domain": "Finance, Crypto & Web3", "summary": "Parses structured-note prospectuses and stress-tests payoffs with Monte Carlo", "readme_summary": "Pipeline with Parser, Quant, MC and Verifier agents to extract barriers and autocalls from SEC filings. Python + Modal sandboxes run 50k correlated GBM paths, payoff diagrams and risk heatmaps.", "tech_highlights": [ "Muse Spark 1M Context", "Modal Sandboxes", "Monte Carlo GBM" ], "created_at": "2026-11-01T18:03:42Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 3, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": false, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.5, "score_meta_tooling": 1.3, "score_tech_depth": 0.6, "score_demo": 0.8, "score_total": 4.2, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "Automated test suite", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ] ] }, "rank": 661, "is_new": true, "commits_delta": 3, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "sharmauncw/ask-the-control-tower", "html_url": "https://github.com/sharmauncw/ask-the-control-tower", "track": "Push the Frontier", "domain": "Education & Knowledge Systems", "summary": "Citation-grounded Q&A assistant that answers only from verified facts", "readme_summary": "Standalone assistant with 10-question bank, fact-store.json as only source of truth, and Meta Model API phrasing layer stubbed. Architecture matches questions, fills templates, withholds on missing values with citations. Stack is HTML/JS with audited placeholder map.", "tech_highlights": [ "Meta Model API", "Fact-Store Grounding", "Vanilla JS App" ], "created_at": "2026-10-27T14:30:40Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 2, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": false, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": true, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.0, "score_meta_tooling": 1.0, "score_tech_depth": 0.8, "score_demo": 0.4, "score_total": 4.2, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "Domain alignment", "+0.3" ], [ "Eval & benchmark proof", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "Automated test suite", "+0.3" ], [ "Agent / eval harness", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ] ] }, "rank": 662, "is_new": false, "commits_delta": 0, "rank_delta": -275, "commits_delta_last_run": 0 }, { "full_name": "synchronic1/AIPSTER", "html_url": "https://github.com/synchronic1/AIPSTER", "track": "Build for Your World", "domain": "General & Emerging Applications", "summary": "Web app with control panel and local worker deployed live at aipster.net", "readme_summary": "AIPSTER ships a web app with control panel, local-worker and tray components. Deployed to aipster.net with versioned releases and deployment.json provenance. Integrates Muse models per hackathon build.", "tech_highlights": [ "Muse Spark", "JS Control Panel", "Local Worker" ], "created_at": "2026-10-26T16:07:57Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 436, "commits_before_window": 0, "prs_total": 60, "prs_merged": 43, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": false, "has_ci": true, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.7, "score_meta_tooling": 0.5, "score_tech_depth": 1.3, "score_demo": 0.6, "score_total": 4.1, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "General domain", "+0.2" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (436)", "+0.6" ], [ "Automated CI workflow", "+0.2" ], [ "PR review workflow (43 PRs)", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 663, "is_new": true, "commits_delta": 436, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "brennandec/meta-ai-hackathon-2026", "html_url": "https://github.com/brennandec/meta-ai-hackathon-2026", "track": "Push the Frontier", "domain": "Developer Tooling, Infra & Security", "summary": "Hackathon harness with contracts, fixtures and launcher for judging runs", "readme_summary": "No README content provided. File tree shows launcher, candidate backend, deploy configs and JSON contracts for judge actions, clock, beats and notices. Appears to be evaluation tooling for reproducible hackathon judging.", "tech_highlights": [ "Node.js + .mjs", "JSON Contracts", "Deploy Automation" ], "created_at": "2026-10-28T17:54:29Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 67, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": true, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.0, "score_meta_tooling": 0.5, "score_tech_depth": 1.2, "score_demo": 0.4, "score_total": 4.1, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "High-impact domain", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ] ], "meta": [ [ "Base", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (67)", "+0.6" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ] ] }, "rank": 664, "is_new": false, "commits_delta": 0, "rank_delta": -332, "commits_delta_last_run": 0 }, { "full_name": "sha-riyat/kaye", "html_url": "https://github.com/sha-riyat/kaye", "track": "Build for Your World", "domain": "Business, Sales & Commerce", "summary": "WhatsApp bookkeeping in French recording sales, debts, receipts for merchants", "readme_summary": "Merchant talks or photographs sales in WhatsApp, agent records sales and debts, confirms before writing and chases payments. FastAPI webhook on Modal with signature verification and dedup, using Muse models. French-first for West Africa.", "tech_highlights": [ "Muse Models", "WhatsApp + FastAPI", "Modal + Alembic" ], "created_at": "2026-10-30T23:38:47Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 17, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.5, "score_meta_tooling": 0.5, "score_tech_depth": 1.3, "score_demo": 0.8, "score_total": 4.1, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ] ], "meta": [ [ "Base", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (17)", "+0.4" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ] ] }, "rank": 665, "is_new": true, "commits_delta": 17, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "tugrulNet/xanthos-residential-ai", "html_url": "https://github.com/tugrulNet/xanthos-residential-ai", "track": "Build for Your World", "domain": "Business, Sales & Commerce", "summary": "Enter a Calgary address to see a livability score explained plus listing photo checks.", "readme_summary": "Calgary home-buyer flow showing a read-only residential livability and investment score. Uses Muse Spark via Meta Model API for plain-language explanations and Python plus SAM 3.1 for listing photo triage and segmentation.", "tech_highlights": [ "SAM 3.1 Vision", "Muse Spark", "Python Pipeline" ], "created_at": "2026-10-26T16:15:29Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 10, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": true, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.3, "score_meta_tooling": 1.6, "score_tech_depth": 0.8, "score_demo": 0.4, "score_total": 4.1, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "5+ window commits (10)", "+0.2" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ] ] }, "rank": 666, "is_new": false, "commits_delta": 0, "rank_delta": -393, "commits_delta_last_run": 0 }, { "full_name": "hombaez-guy/meta-hackathon", "html_url": "https://github.com/hombaez-guy/meta-hackathon", "track": "Build for Your World", "domain": "General & Emerging Applications", "summary": "Generic Python backend experiment with MongoDB storage and Docker setup", "readme_summary": "Minimal Python project with Docker Compose, MongoDB store, and cron jobs. README gives no product detail; file tree suggests backend agent or data service prototype.", "tech_highlights": [ "Python", "MongoDB + Docker", "Docker Compose" ], "created_at": "2026-10-26T19:18:10Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 5, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": true, "has_tests": false, "has_src": true, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.8, "score_meta_tooling": 0.5, "score_tech_depth": 1.0, "score_demo": 0.8, "score_total": 4.1, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "General domain", "+0.2" ], [ "Docker packaging", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ] ], "meta": [ [ "Base", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "5+ window commits (5)", "+0.2" ], [ "Modular src/ architecture", "+0.3" ], [ "Agent / eval harness", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ] ] }, "rank": 667, "is_new": false, "commits_delta": 1, "rank_delta": -207, "commits_delta_last_run": 0 }, { "full_name": "khanzzirfan/pixitween-director", "html_url": "https://github.com/khanzzirfan/pixitween-director", "track": "Build for Your World", "domain": "Gaming, Entertainment & Creative Media", "summary": "Turns one product photo into an editable animated film timeline in the browser.", "readme_summary": "Plans a Muse Spark agent that writes a layered PixiJS animation timeline from a brief. Text stays as editable DOM for correct spelling, all layers chat-editable. Early plan stage, no working app yet, uses Muse Spark for storyboarding.", "tech_highlights": [ "Muse Spark", "PixiJS Engine", "Browser Timeline" ], "created_at": "2026-10-28T08:47:10Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 4, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": false, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": true, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 1, "score_impact": 1.2, "score_meta_tooling": 1.8, "score_tech_depth": 0.3, "score_demo": 0.8, "score_total": 4.1, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "General domain", "+0.2" ] ], "meta": [ [ "Base", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ], [ "Open-weights / fine-tuning", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ] ] }, "rank": 668, "is_new": true, "commits_delta": 4, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "kevalhirani2003/streetops-ai", "html_url": "https://github.com/kevalhirani2003/streetops-ai", "track": "Build for Your World", "domain": "Healthcare, Civic Tech & Sustainability", "summary": "Agentic assistant turning street-damage reports into audited work orders", "readme_summary": "StreetOps AI converts unstructured pothole and streetlight reports into verified maintenance work orders. Stack is React Vite plus Node Express with a Muse Spark agent loop for extraction, deduplication and auditable history.", "tech_highlights": [ "Muse Spark", "React + Express", "Supabase Postgres" ], "created_at": "2026-10-26T09:47:49Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 3, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": true, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.4, "score_meta_tooling": 1.3, "score_tech_depth": 0.6, "score_demo": 0.8, "score_total": 4.1, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "High-impact domain", "+0.4" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ] ] }, "rank": 669, "is_new": false, "commits_delta": 0, "rank_delta": -318, "commits_delta_last_run": 0 }, { "full_name": "Dreadfulgamerkid/The-Cyber-Crew-Goes-Meta", "html_url": "https://github.com/Dreadfulgamerkid/The-Cyber-Crew-Goes-Meta", "track": "Build for Your World", "domain": "Gaming, Entertainment & Creative Media", "summary": "Linux terminal adventure game with AI-generated storybooks", "readme_summary": "The Cyber Crew is a web game for learning Linux terminal via adventures. Built with Vite and TypeScript, it calls Meta Model API muse-spark-1.2 for book generation with fallback to a built-in procedural generator.", "tech_highlights": [ "Muse Spark 1.2", "Vite + TypeScript", "Meta Model API" ], "created_at": "2026-10-29T07:52:22Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 3, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": true, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.4, "score_meta_tooling": 1.3, "score_tech_depth": 0.6, "score_demo": 0.8, "score_total": 4.1, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "General domain", "+0.2" ], [ "Multi-module scope (>10 files)", "+0.2" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ] ] }, "rank": 670, "is_new": false, "commits_delta": 0, "rank_delta": -362, "commits_delta_last_run": 0 }, { "full_name": "niteash/hsain-agent", "html_url": "https://github.com/niteash/hsain-agent", "track": "Build for Your World", "domain": "Business, Sales & Commerce", "summary": "Voice and shelf-photo back-office agent for small retail stock and reorder", "readme_summary": "Owner sends voice note plus shelf photo/video or invoice, agent returns verified stock check and supplier reorder. Built with Muse Spark, SAM 3.1 and Muse Voice Transcribe, frontend plus backend.", "tech_highlights": [ "Muse Spark", "SAM 3.1 Vision", "Muse Voice Transcribe" ], "created_at": "2026-10-27T09:32:42Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 3, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": true, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.3, "score_meta_tooling": 1.8, "score_tech_depth": 0.6, "score_demo": 0.4, "score_total": 4.1, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ] ], "tech": [ [ "Base", "+0.3" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ] ] }, "rank": 671, "is_new": true, "commits_delta": 3, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "arinde/shopThread", "html_url": "https://github.com/arinde/shopThread", "track": "Build for Your World", "domain": "Business, Sales & Commerce", "summary": "Product list to shareable storefront with WhatsApp checkout", "readme_summary": "Next.js storefront builder where vendors create a store slug, customers browse and checkout, orders go to WhatsApp and dashboard. Stack is Next.js, Supabase Auth/Postgres, and WhatsApp formatting. No Meta AI / Muse usage documented.", "tech_highlights": [ "Next.js + Supabase", "WhatsApp Checkout", "Storefront Builder" ], "created_at": "2026-10-26T21:38:04Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 2, "commits_before_window": 1, "prs_total": 0, "prs_merged": 0, "is_preexisting": true, "has_docker": false, "has_tests": false, "has_src": true, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": true, "video_urls": [ "https://youtu.be/R41-tiytYAU" ], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.5, "score_meta_tooling": 0.5, "score_tech_depth": 0.2, "score_demo": 1.9, "score_total": 4.1, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ] ], "meta": [ [ "Base", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Pre-existing repo (<=2 commits)", "-0.5" ] ], "demo": [ [ "Base", "+0.4" ], [ "Video walkthrough", "+1.1" ], [ "Reproducible setup guide", "+0.4" ] ] }, "rank": 672, "is_new": true, "commits_delta": 2, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "martinambrus/clipmonger", "html_url": "https://github.com/martinambrus/clipmonger", "track": "Build for Your World", "domain": "General & Emerging Applications", "summary": "Highly configurable cross-platform clipboard manager", "readme_summary": "Highly configurable cross-platform clipboard manager", "tech_highlights": [], "created_at": "2026-10-24T11:14:34Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 153, "commits_before_window": 3, "prs_total": 19, "prs_merged": 18, "is_preexisting": true, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.4, "score_meta_tooling": 0.5, "score_tech_depth": 1.7, "score_demo": 0.4, "score_total": 4.0, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "General domain", "+0.2" ], [ "Multi-module scope (>10 files)", "+0.2" ] ], "meta": [ [ "Base", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (153)", "+0.6" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "PR review workflow (18 PRs)", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ] ] }, "rank": 673, "is_new": true, "commits_delta": 153, "rank_delta": 0, "commits_delta_last_run": 1 }, { "full_name": "omenking/meta-global-ai-hackathon-jolly-challenge", "html_url": "https://github.com/omenking/meta-global-ai-hackathon-jolly-challenge", "track": "Build for Your World", "domain": "Gaming, Entertainment & Creative Media", "summary": "Tile puzzle game in Chip's Challenge style with AI-generated levels.", "readme_summary": "Jolly's Challenge is a tile-based puzzle game testing if AI can generate fun levels. Uses a Python game engine with YAML levels, scripts and asset tools. Leverages Meta models for level generation and art iteration.", "tech_highlights": [ "Python Game Engine", "AI Level Generation", "YAML + Tile Art" ], "created_at": "2026-10-26T17:34:56Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 112, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": true, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.7, "score_meta_tooling": 0.5, "score_tech_depth": 1.2, "score_demo": 0.6, "score_total": 4.0, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "General domain", "+0.2" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (112)", "+0.6" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 674, "is_new": true, "commits_delta": 112, "rank_delta": 0, "commits_delta_last_run": 13 }, { "full_name": "dandan002/secfin-muse", "html_url": "https://github.com/dandan002/secfin-muse", "track": "Build for Your World", "domain": "Finance, Crypto & Web3", "summary": "Automation tool for securities finance workflows", "readme_summary": "Automates securities finance workflows. Layout with platform, infra, mocks and spec.md suggests backend service design. Implied Meta AI / Muse integration for finance automation.", "tech_highlights": [ "Securities Finance", "Workflow Automation", "Muse Spark" ], "created_at": "2026-10-27T01:00:16Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 61, "commits_before_window": 0, "prs_total": 19, "prs_merged": 19, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": false, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.3, "score_meta_tooling": 0.5, "score_tech_depth": 1.4, "score_demo": 0.8, "score_total": 4.0, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (61)", "+0.6" ], [ "Automated test suite", "+0.3" ], [ "PR review workflow (19 PRs)", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ] ] }, "rank": 675, "is_new": false, "commits_delta": 47, "rank_delta": -253, "commits_delta_last_run": 0 }, { "full_name": "kuya-kevin/lattice", "html_url": "https://github.com/kuya-kevin/lattice", "track": "Build for Your World", "domain": "Voice, Speech & Audio AI", "summary": "Mini-DAW where AI acts as sound designer and session engineer", "readme_summary": "Browser-based mini digital audio workstation with Muse as creative assistant for sound design and mixing. App directory with docs, spikes, and envs suggests Next.js prototype. Focuses on music creation workflow with AI session help.", "tech_highlights": [ "Muse Audio", "Mini-DAW Web App", "Next.js Prototype" ], "created_at": "2026-10-27T01:39:54Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 59, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": true, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.5, "score_meta_tooling": 0.5, "score_tech_depth": 1.2, "score_demo": 0.8, "score_total": 4.0, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ] ], "meta": [ [ "Base", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (59)", "+0.6" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ] ] }, "rank": 676, "is_new": true, "commits_delta": 59, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "TheWayOfCoding/TWOC-Studio-Manager", "html_url": "https://github.com/TheWayOfCoding/TWOC-Studio-Manager", "track": "Build for Your World", "domain": "Gaming, Entertainment & Creative Media", "summary": "One-click LAN control for studio power, lights, OBS and screens", "readme_summary": "Studio Hub runs on Raspberry Pi or Windows host driving USB-DMX, Kasa, IR and GVM-BLE with modes engine and OBS integration. Backend FastAPI/Uvicorn with pytest and Test Bench UI. Adds AI lighting director layer.", "tech_highlights": [ "FastAPI + OBS", "DMX Lighting", "Raspberry Pi Hub" ], "created_at": "2026-10-28T22:50:30Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 20, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.4, "score_meta_tooling": 0.5, "score_tech_depth": 1.3, "score_demo": 0.8, "score_total": 4.0, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "General domain", "+0.2" ], [ "Multi-module scope (>10 files)", "+0.2" ] ], "meta": [ [ "Base", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (20)", "+0.4" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ] ] }, "rank": 677, "is_new": true, "commits_delta": 20, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "tejasai1/Flowtrace", "html_url": "https://github.com/tejasai1/Flowtrace", "track": "Push the Frontier", "domain": "Developer Tooling, Infra & Security", "summary": "Maps data flows across repos and traces change impact", "readme_summary": "AI agent that infers cross-repository data flows, generates data flow diagrams, and traces change impact. Built with Meta Muse Spark, Python package with YAML config and analysis scripts.", "tech_highlights": [ "Muse Spark", "Python Agent", "Dataflow Analysis" ], "created_at": "2026-10-29T15:19:42Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 15, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": true, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.8, "score_meta_tooling": 0.8, "score_tech_depth": 1.0, "score_demo": 0.4, "score_total": 4.0, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "High-impact domain", "+0.4" ] ], "meta": [ [ "Base", "+0.5" ], [ "Muse Spark integration", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (15)", "+0.4" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ] ] }, "rank": 678, "is_new": true, "commits_delta": 15, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "SaintSinC/pocket-muse", "html_url": "https://github.com/SaintSinC/pocket-muse", "track": "Build for Your World", "domain": "Voice, Speech & Audio AI", "summary": "Pocket voice gadget that answers aloud with cards and images on display", "readme_summary": "Pocket Muse is a round-display device: press button, speak, get voice plus visuals. Brain service handles weather, gold prices and image generation. Uses Muse Spark via Meta Model API for Indie Build for Your World entry.", "tech_highlights": [ "Muse Spark", "Meta Model API", "Voice + display" ], "created_at": "2026-10-27T16:42:33Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 11, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": false, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": true, "has_eval_benchmarks": false, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 1, "score_impact": 1.3, "score_meta_tooling": 1.8, "score_tech_depth": 0.5, "score_demo": 0.4, "score_total": 4.0, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "Open-weights / fine-tuning", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "5+ window commits (11)", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ] ] }, "rank": 679, "is_new": false, "commits_delta": 1, "rank_delta": -319, "commits_delta_last_run": 0 }, { "full_name": "EtienneLescot/shouldercut", "html_url": "https://github.com/EtienneLescot/shouldercut", "track": "Build for Your World", "domain": "Gaming, Entertainment & Creative Media", "summary": "Voice-controlled video editor that cuts footage and generates live shader effects", "readme_summary": "Talk-to-cut editor with WebCodecs VideoDecoder, WebGPU rendering, and MCP-generated WGSL effects. SAM 3.1 mask tracks drive object effects. Uses Meta models via MCP for FX code and object tracking.", "tech_highlights": [ "SAM 3.1 Vision", "WebGPU + WebCodecs", "MCP WGSL Effects" ], "created_at": "2026-10-27T10:45:49Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 7, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": true, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.7, "score_meta_tooling": 1.1, "score_tech_depth": 0.8, "score_demo": 0.4, "score_total": 4.0, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "General domain", "+0.2" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "5+ window commits (7)", "+0.2" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ] ] }, "rank": 680, "is_new": false, "commits_delta": 6, "rank_delta": -262, "commits_delta_last_run": 0 }, { "full_name": "trivnvdev-41/voice-meta-ai-hackathon-2026", "html_url": "https://github.com/trivnvdev-41/voice-meta-ai-hackathon-2026", "track": "Build for Your World", "domain": "Voice, Speech & Audio AI", "summary": "WhatsApp voice sous-chef that saves family recipes and cooks along hands-free", "readme_summary": "WhatsApp voice notes transcribed then structured by Meta Llama into recipes with folk-to-metric measures. Docker setup with Asterisk gateway plus worker; calls back to guide cooking step-by-step by voice.", "tech_highlights": [ "Meta Llama", "WhatsApp Voice", "Asterisk + Docker" ], "created_at": "2026-10-28T08:04:32Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 6, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": true, "has_tests": false, "has_src": false, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.0, "score_meta_tooling": 0.5, "score_tech_depth": 0.5, "score_demo": 1.0, "score_total": 4.0, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Docker packaging", "+0.4" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "5+ window commits (6)", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 681, "is_new": false, "commits_delta": 0, "rank_delta": -318, "commits_delta_last_run": 0 }, { "full_name": "devian-321/meta-hackathon-2026", "html_url": "https://github.com/devian-321/meta-hackathon-2026", "track": "Push the Frontier", "domain": "Developer Tooling, Infra & Security", "summary": "FaultLine CI workspace for GitLab validation and submission automation", "readme_summary": "Developer tooling workspace for FaultLine CI with GitLab runbook, validation docs and scripts. Includes faultline-ci service, tests and demo script. Focus is CI reliability and submission evidence, not Muse inference.", "tech_highlights": [ "GitLab CI Tooling", "Validation Scripts", "DevOps Automation" ], "created_at": "2026-10-23T14:37:36Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 3, "commits_before_window": 5, "prs_total": 0, "prs_merged": 0, "is_preexisting": true, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.8, "score_meta_tooling": 0.5, "score_tech_depth": 0.9, "score_demo": 0.8, "score_total": 4.0, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "High-impact domain", "+0.4" ] ], "meta": [ [ "Base", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ] ] }, "rank": 682, "is_new": false, "commits_delta": 0, "rank_delta": -241, "commits_delta_last_run": 0 }, { "full_name": "0b10headedcalf/holomenu", "html_url": "https://github.com/0b10headedcalf/holomenu", "track": "Build for Your World", "domain": "Business, Sales & Commerce", "summary": "Turns real food photos into 3D previews with TruthScore for ordering", "readme_summary": "Creates rotatable true-scale 3D dishes from customer photos with evidence strip and TruthScore. Next.js frontend with Modal 3D backend, cached instant models and conversational spatial Q&A.", "tech_highlights": [ "Next.js + Modal", "3D Reconstruction", "TruthScore + Q&A" ], "created_at": "2026-10-29T19:11:45Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 3, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": true, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.5, "score_meta_tooling": 1.1, "score_tech_depth": 0.6, "score_demo": 0.8, "score_total": 4.0, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ] ], "meta": [ [ "Base", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ] ] }, "rank": 683, "is_new": true, "commits_delta": 3, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "Dav2022/TrueLanded-Meta-Hackathon-2026", "html_url": "https://github.com/Dav2022/TrueLanded-Meta-Hackathon-2026", "track": "Build for Your World", "domain": "Legal & Compliance", "summary": "Offline evidence-to-decision demo recalculating obligations and invoices", "readme_summary": "Static browser demo with deterministic engine verifying synthetic source data, tracking conflicts, and ranking missing evidence. Meta Muse Spark 1.3 used offline for historical text extraction only; demo makes no live calls. Requires human review.", "tech_highlights": [ "Muse Spark 1.3", "WebCrypto Demo", "Python Tests" ], "created_at": "2026-10-29T21:36:51Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 3, "commits_before_window": 0, "prs_total": 1, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": true, "live_urls": [ "https://dav2022.github.io/TrueLanded-Meta-Hackathon-2026/", "https://dav2022.github.io/TrueLanded-Meta-Hackathon-2026/adjudication.html" ], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.5, "score_meta_tooling": 0.8, "score_tech_depth": 0.9, "score_demo": 0.8, "score_total": 4.0, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ] ], "meta": [ [ "Base", "+0.5" ], [ "Muse Spark integration", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Live web deployment", "+0.4" ] ] }, "rank": 684, "is_new": true, "commits_delta": 3, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "abhijeet4725/SiteCheck", "html_url": "https://github.com/abhijeet4725/SiteCheck", "track": "Build for Your World", "domain": "Multimodal Vision & Video (SAM / Vision)", "summary": "Phone-photo home screening that finds cracks and damp and rates severity", "readme_summary": "Plans photo upload with A4 scale reference, SAM 3.1 segmentation for cracks/damp, OpenCV measurement, and Muse Spark classification to JSON defect report. Stack is Python, SAM 3.1, Meta Model API, OpenCV, NumPy, Gradio. Early planned status, screening aid only.", "tech_highlights": [ "SAM 3.1 Vision", "Muse Spark", "OpenCV + Gradio" ], "created_at": "2026-10-26T08:19:57Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 2, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": false, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.3, "score_meta_tooling": 1.6, "score_tech_depth": 0.3, "score_demo": 0.8, "score_total": 4.0, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ] ] }, "rank": 685, "is_new": false, "commits_delta": 0, "rank_delta": -332, "commits_delta_last_run": 0 }, { "full_name": "manju89jay/navfail", "html_url": "https://github.com/manju89jay/navfail", "track": "Push the Frontier", "domain": "Robotics, IoT & Manufacturing", "summary": "Agent that investigates Nav2 navigation failures in Gazebo and explains causes via repeat runs", "readme_summary": "navfail automates Nav2 failure diagnosis: collects logs, reproduces faults in Gazebo, checks intermittency and tests config fixes. Stack is ROS 2 Nav2 with Gazebo simulation and incident reproduction scripts. Plans to use Meta AI / Muse models for hypothesis generation from logs.", "tech_highlights": [ "ROS 2 Nav2", "Gazebo Sim", "Muse Spark" ], "created_at": "2026-10-26T10:27:57Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 1, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": false, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.1, "score_meta_tooling": 1.0, "score_tech_depth": 0.3, "score_demo": 0.6, "score_total": 4.0, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "High-impact domain", "+0.4" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 686, "is_new": false, "commits_delta": 0, "rank_delta": -345, "commits_delta_last_run": 0 }, { "full_name": "riteshth1/ReceiptIQ-AI", "html_url": "https://github.com/riteshth1/ReceiptIQ-AI", "track": "Push the Frontier", "domain": "Developer Tooling, Infra & Security", "summary": "Independent verifier that checks AI coding patches against tests and evidence", "readme_summary": "Plans and edits code in an isolated workspace, runs real tests, and has an independent verifier challenge the patch. Built with FastAPI backend and frontend with pytest harness. Uses Meta Muse Spark to plan, edit, and judge claims with evidence receipt.", "tech_highlights": [ "Muse Spark", "FastAPI Backend", "Pytest Verification" ], "created_at": "2026-11-01T18:35:59Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 1, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.8, "score_meta_tooling": 0.5, "score_tech_depth": 0.9, "score_demo": 0.8, "score_total": 4.0, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "High-impact domain", "+0.4" ] ], "meta": [ [ "Base", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ] ] }, "rank": 687, "is_new": true, "commits_delta": 1, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "madazz01/meta-betta", "html_url": "https://github.com/madazz01/meta-betta", "track": "Push the Frontier", "domain": "Developer Tooling, Infra & Security", "summary": "VS Code chat companion for Muse Code that remembers you and your project", "readme_summary": "A VS Code extension chat panel workmate for Muse Code with a persistent brain folder for memory across sessions. Built during the hackathon with extension plus spike prototype. Uses Meta Muse models for conversational coding assistance.", "tech_highlights": [ "Muse Spark", "VS Code Extension", "Persistent Memory" ], "created_at": "2026-10-28T04:32:16Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 76, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": false, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.8, "score_meta_tooling": 0.8, "score_tech_depth": 0.9, "score_demo": 0.4, "score_total": 3.9, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "High-impact domain", "+0.4" ] ], "meta": [ [ "Base", "+0.5" ], [ "Muse Spark integration", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (76)", "+0.6" ] ], "demo": [ [ "Base", "+0.4" ] ] }, "rank": 688, "is_new": true, "commits_delta": 76, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "jerryOkafor/kadent-ai", "html_url": "https://github.com/jerryOkafor/kadent-ai", "track": "Build for Your World", "domain": "Business, Sales & Commerce", "summary": "Receipt photo updates shopping lists, prices, budgets and weekly plans", "readme_summary": "Firebase Cloud Function proxy validates Firebase token, quota and forwards to Meta Model API, logging only calls. Client library handles receipt reading, auto-filing and list planning. Built on Meta Muse models.", "tech_highlights": [ "Muse Models", "Firebase Functions", "Receipt Vision AI" ], "created_at": "2026-10-28T03:12:48Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 38, "commits_before_window": 0, "prs_total": 11, "prs_merged": 11, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": true, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.5, "score_meta_tooling": 0.8, "score_tech_depth": 1.2, "score_demo": 0.4, "score_total": 3.9, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ] ], "meta": [ [ "Base", "+0.5" ], [ "Muse Spark integration", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (38)", "+0.4" ], [ "Modular src/ architecture", "+0.3" ], [ "PR review workflow (11 PRs)", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ] ] }, "rank": 689, "is_new": false, "commits_delta": 16, "rank_delta": -332, "commits_delta_last_run": 0 }, { "full_name": "dylanHulin/multimodal-game-architect", "html_url": "https://github.com/dylanHulin/multimodal-game-architect", "track": "Build for Your World", "domain": "Gaming, Entertainment & Creative Media", "summary": "Generates game docs, Unity/Godot code and art from prompts or sketches", "readme_summary": "Agentic pipeline turns ideas into GDDs, C#/GDScript controllers and 2D assets packaged as zip. Backend is Python FastAPI with Meta Model APIs, frontend React/Next.js. Uses Llama 3, Muse Code and Muse Image.", "tech_highlights": [ "Llama 3 GDD Agent", "Muse Code + Image", "FastAPI + Next.js" ], "created_at": "2026-10-29T16:35:03Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 14, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": true, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.2, "score_meta_tooling": 1.5, "score_tech_depth": 0.8, "score_demo": 0.4, "score_total": 3.9, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "General domain", "+0.2" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ] ], "tech": [ [ "Base", "+0.3" ], [ "5+ window commits (14)", "+0.2" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ] ] }, "rank": 690, "is_new": true, "commits_delta": 14, "rank_delta": 0, "commits_delta_last_run": 1 }, { "full_name": "EmirCobanOfficial/courtsense-site", "html_url": "https://github.com/EmirCobanOfficial/courtsense-site", "track": "Build for Your World", "domain": "Multimodal Vision & Video (SAM / Vision)", "summary": "Landing page for tennis video to movement data with SAM 3.1", "readme_summary": "Static landing site for CourtSense, which converts tennis training video into movement data. Built during the hackathon with HTML and hosted on GitHub Pages; core analysis uses SAM 3.1 and Muse Spark 1.3 in main repo.", "tech_highlights": [ "SAM 3.1 Vision", "Muse Spark 1.3", "Static HTML Site" ], "created_at": "2026-10-28T17:56:49Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 9, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": false, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": true, "live_urls": [ "https://emircobanofficial.github.io/courtsense-site/" ], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.5, "score_meta_tooling": 1.1, "score_tech_depth": 0.5, "score_demo": 0.8, "score_total": 3.9, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ] ], "meta": [ [ "Base", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "5+ window commits (9)", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Live web deployment", "+0.4" ] ] }, "rank": 691, "is_new": false, "commits_delta": 8, "rank_delta": -276, "commits_delta_last_run": 0 }, { "full_name": "danielmedinac22/amanece-meta-hackathon", "html_url": "https://github.com/danielmedinac22/amanece-meta-hackathon", "track": "Build for Your World", "domain": "Business, Sales & Commerce", "summary": "Conversational builder that creates 24/7 WhatsApp agents for Latin American businesses", "readme_summary": "Amanece lets owners chat to build WhatsApp customer agents with rules, sections and metrics. Stack is Next.js + Drizzle + Neon with Kapso WhatsApp integration. Uses Muse Spark via Meta Models API as owner and customer agents.", "tech_highlights": [ "Muse Spark", "Next.js + Neon", "WhatsApp via Kapso" ], "created_at": "2026-10-27T03:37:21Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 8, "commits_before_window": 0, "prs_total": 8, "prs_merged": 2, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": true, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.5, "score_meta_tooling": 0.8, "score_tech_depth": 0.8, "score_demo": 0.8, "score_total": 3.9, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ] ], "meta": [ [ "Base", "+0.5" ], [ "Muse Spark integration", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "5+ window commits (8)", "+0.2" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ] ] }, "rank": 692, "is_new": false, "commits_delta": 0, "rank_delta": -345, "commits_delta_last_run": 0 }, { "full_name": "YasuruThilakshana/AnimalID", "html_url": "https://github.com/YasuruThilakshana/AnimalID", "track": "Build for Your World", "domain": "Multimodal Vision & Video (SAM / Vision)", "summary": "Registers pets, identifies them by photo scan and manages lost-and-found alerts.", "readme_summary": "React Vite + Tailwind frontend with Express Sequelize MySQL backend for pet registration. POST /api/animals/scan uses Meta SAM 3.1 for photo identification, uploads served via /uploads.", "tech_highlights": [ "SAM 3.1 Vision", "React + Express", "MySQL + Sequelize" ], "created_at": "2026-10-28T09:25:08Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 7, "commits_before_window": 0, "prs_total": 2, "prs_merged": 2, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": true, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.5, "score_meta_tooling": 0.8, "score_tech_depth": 0.8, "score_demo": 0.8, "score_total": 3.9, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ] ], "meta": [ [ "Base", "+0.5" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "5+ window commits (7)", "+0.2" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ] ] }, "rank": 693, "is_new": true, "commits_delta": 7, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "Clesic/META-Hackathon---TacitOS", "html_url": "https://github.com/Clesic/META-Hackathon---TacitOS", "track": "Build for Your World", "domain": "Business, Sales & Commerce", "summary": "Rehearses a purchasing case so successors learn the missing expert condition", "readme_summary": "Missing Monday demo runs a synthetic purchasing case where a successor rehearses and an expert adds the missing condition. Built with Python stdlib server on port 8766 with no dependencies. Uses muse-spark-open-1026 via BASETEN_API_KEY when present, otherwise runs offline.", "tech_highlights": [ "Muse Spark Open", "Python Stdlib Server", "Synthetic Case Rehearsal" ], "created_at": "2026-10-26T16:26:50Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 6, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": false, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": true, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.3, "score_meta_tooling": 1.3, "score_tech_depth": 0.5, "score_demo": 0.8, "score_total": 3.9, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "Open-weights / fine-tuning", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "5+ window commits (6)", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ] ] }, "rank": 694, "is_new": false, "commits_delta": 0, "rank_delta": -268, "commits_delta_last_run": 0 }, { "full_name": "Hyatus-Living/arosa-housing-modeling", "html_url": "https://github.com/Hyatus-Living/arosa-housing-modeling", "track": "Build for Your World", "domain": "Multimodal Vision & Video (SAM / Vision)", "summary": "Zoning and home design tool with editable plans and walkthrough", "readme_summary": "Extracts housing research with SAM 3.1 photo selection, Muse Image illustration with provenance, editable floor-plan viewers and first-person walkthrough. Includes NYC address resolution and IFC intake. Live calls need MODEL_API_KEY, tests use stubs.", "tech_highlights": [ "SAM 3.1 Vision", "Muse Image", "Muse Spark Research" ], "created_at": "2026-10-28T01:20:26Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 2, "commits_before_window": 0, "prs_total": 1, "prs_merged": 1, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": false, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.5, "score_meta_tooling": 1.3, "score_tech_depth": 0.3, "score_demo": 0.8, "score_total": 3.9, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ] ], "meta": [ [ "Base", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ] ], "tech": [ [ "Base", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ] ] }, "rank": 695, "is_new": false, "commits_delta": 0, "rank_delta": -323, "commits_delta_last_run": 0 }, { "full_name": "thecurtisloucks/sitememory", "html_url": "https://github.com/thecurtisloucks/sitememory", "track": "Build for Your World", "domain": "Multimodal Vision & Video (SAM / Vision)", "summary": "Spatial memory app that records rooms and answers questions with visual proof", "readme_summary": "Records physical environments, tracks observations over time, and serves a React dashboard over Fastify API with Prisma SQLite persistence. Monorepo uses React, Vite, Tailwind, Fastify, Zod, TypeScript. Meta inference for image scanning deferred to Milestone 2.", "tech_highlights": [ "React + Vite + Tailwind", "Fastify + Prisma", "TypeScript Monorepo" ], "created_at": "2026-10-30T23:27:30Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 2, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": true, "has_ci": true, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.5, "score_meta_tooling": 0.8, "score_tech_depth": 0.8, "score_demo": 0.8, "score_total": 3.9, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ] ], "meta": [ [ "Base", "+0.5" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Automated CI workflow", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ] ] }, "rank": 696, "is_new": true, "commits_delta": 2, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "roldhaa/AgentFoundry", "html_url": "https://github.com/roldhaa/AgentFoundry", "track": "Push the Frontier", "domain": "Autonomous Agents & Workflow Automation", "summary": "Builds business agents and verifies them in simulated environments with checks", "readme_summary": "Platform to define missions, generate versioned agents, and run them in isolated business simulations. Verifies outcomes against deterministic business rules and analyzes failures. Uses Meta AI agent reasoning with execution feedback.", "tech_highlights": [ "Agent Simulation", "Outcome Verifier", "Muse Models" ], "created_at": "2026-10-31T02:01:45Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 2, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": false, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.8, "score_meta_tooling": 1.0, "score_tech_depth": 0.3, "score_demo": 0.8, "score_total": 3.9, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "High-impact domain", "+0.4" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ] ] }, "rank": 697, "is_new": true, "commits_delta": 2, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "Vaibhavs18/adfarming", "html_url": "https://github.com/Vaibhavs18/adfarming", "track": "Build for Your World", "domain": "Gaming, Entertainment & Creative Media", "summary": "Brief-to-ad pipeline generating concepts, storyboards and platform-ready cuts with logs", "readme_summary": "Five-stage flow: Muse Spark creates 3 ad concepts, Muse Image makes storyboards, SAM 3.1 keeps framing across aspect ratios with voice transcription. Every step emits JSON contract traces. Handoff stages draft package for Meta Ads Manager.", "tech_highlights": [ "Muse Spark", "SAM 3.1 Vision", "Muse Image + Voice" ], "created_at": "2026-10-27T20:13:41Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 1, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": true, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.2, "score_meta_tooling": 1.3, "score_tech_depth": 0.6, "score_demo": 0.8, "score_total": 3.9, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "General domain", "+0.2" ] ], "meta": [ [ "Base", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ] ], "tech": [ [ "Base", "+0.3" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ] ] }, "rank": 698, "is_new": false, "commits_delta": 0, "rank_delta": -323, "commits_delta_last_run": 0 }, { "full_name": "Alafedoyinsola/cleardesk-ai", "html_url": "https://github.com/Alafedoyinsola/cleardesk-ai", "track": "Build for Your World", "domain": "Business, Sales & Commerce", "summary": "AI-assisted invoice reviewer that flags missing data and queues items for human review", "readme_summary": "Prototype for small businesses to submit invoice text and get missing-field and inconsistency findings. Backend calls Meta Model API, frontend manages queue and reviewed state in local storage. Human-in-loop design never auto-approves or pays invoices.", "tech_highlights": [ "Meta Model API", "React + Vite", "Express Backend" ], "created_at": "2026-10-29T09:55:35Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 1, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": true, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.5, "score_meta_tooling": 1.0, "score_tech_depth": 0.6, "score_demo": 0.8, "score_total": 3.9, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ] ] }, "rank": 699, "is_new": true, "commits_delta": 1, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "sylwesterdigital/cv-meta-hackathon-solvi-help", "html_url": "https://github.com/sylwesterdigital/cv-meta-hackathon-solvi-help", "track": "Build for Your World", "domain": "General & Emerging Applications", "summary": "Meta AI helper app built from scratch for everyday help and guidance", "readme_summary": "Lightweight project built from scratch around Meta AI for the hackathon. Includes backend, JS frontend, PWA manifest and tests. Uses Meta AI models for assistance via web interface.", "tech_highlights": [ "Meta AI", "JavaScript PWA", "Node Backend" ], "created_at": "2026-10-26T16:44:19Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 126, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 2, "score_impact": 1.4, "score_meta_tooling": 0.5, "score_tech_depth": 1.5, "score_demo": 0.4, "score_total": 3.8, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "General domain", "+0.2" ], [ "Multi-module scope (>10 files)", "+0.2" ] ], "meta": [ [ "Base", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (126)", "+0.6" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ] ] }, "rank": 700, "is_new": false, "commits_delta": 79, "rank_delta": -387, "commits_delta_last_run": 0 }, { "full_name": "bharatvamsi34/billsaathi", "html_url": "https://github.com/bharatvamsi34/billsaathi", "track": "Build for Your World", "domain": "Finance, Crypto & Web3", "summary": "Agent that verifies Indian bills and flags scams before payment.", "readme_summary": "AI agent to verify bills and payment requests for Indian users and catch fraud. Repo has web client, API backend, evals, infra and docs for verification workflow. Uses Meta models for document checks and risk explanation.", "tech_highlights": [ "Fraud Detection", "Bill Verification", "Web + API" ], "created_at": "2026-10-27T03:26:27Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 31, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": false, "has_ci": true, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": true, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.8, "score_meta_tooling": 0.5, "score_tech_depth": 1.1, "score_demo": 0.4, "score_total": 3.8, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Eval & benchmark proof", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ] ], "meta": [ [ "Base", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (31)", "+0.4" ], [ "Agent / eval harness", "+0.2" ], [ "Automated CI workflow", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ] ] }, "rank": 701, "is_new": false, "commits_delta": 21, "rank_delta": -302, "commits_delta_last_run": 0 }, { "full_name": "georgethetaco44-bit/Pulsar-VST", "html_url": "https://github.com/georgethetaco44-bit/Pulsar-VST", "track": "Build for Your World", "domain": "Gaming, Entertainment & Creative Media", "summary": "AI-powered VST synthesizer plugin built with JUCE and C++", "readme_summary": "C++ JUCE-based VST synth with CMake build, resources and tests. AI-powered sound generation and preset logic for DAWs. Integrates Meta AI / Muse for sound control.", "tech_highlights": [ "C++ JUCE VST", "AI Synth Engine", "CMake Build" ], "created_at": "2026-10-30T01:05:05Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 30, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": true, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.4, "score_meta_tooling": 0.5, "score_tech_depth": 1.5, "score_demo": 0.4, "score_total": 3.8, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "General domain", "+0.2" ], [ "Multi-module scope (>10 files)", "+0.2" ] ], "meta": [ [ "Base", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (30)", "+0.4" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Automated CI workflow", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ] ] }, "rank": 702, "is_new": true, "commits_delta": 30, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "mkhsu2002/Agentic-Life-World-Studio", "html_url": "https://github.com/mkhsu2002/Agentic-Life-World-Studio", "track": "Build for Your World", "domain": "Gaming, Entertainment & Creative Media", "summary": "Author studio that turns original works into a persistent multilingual world site.", "readme_summary": "Private AI Studio ingests text, Word, PDF, and images to draft world settings for author approval and visual checks. Central world database stores canon, versions, and multilingual names for consistent publishing. Vite + TypeScript site deployed via Cloudflare.", "tech_highlights": [ "Vite + TypeScript", "Cloudflare Deploy", "Multilingual CMS" ], "created_at": "2026-10-26T16:58:02Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 23, "commits_before_window": 0, "prs_total": 1, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": true, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.4, "score_meta_tooling": 0.5, "score_tech_depth": 1.5, "score_demo": 0.4, "score_total": 3.8, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "General domain", "+0.2" ], [ "Multi-module scope (>10 files)", "+0.2" ] ], "meta": [ [ "Base", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (23)", "+0.4" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Automated CI workflow", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ] ] }, "rank": 703, "is_new": false, "commits_delta": 0, "rank_delta": -415, "commits_delta_last_run": 0 }, { "full_name": "kixorz/meta-hackathon-aipool", "html_url": "https://github.com/kixorz/meta-hackathon-aipool", "track": "Build for Your World", "domain": "Robotics, IoT & Manufacturing", "summary": "Automates pool filter backwashing with pressure sensing, valves and pump control.", "readme_summary": "ESP32-based controller reads filter pressure gauge, drives pump and backwash valve with HTTP server and Home Assistant integration. Includes mDNS, config manager and relay control. Plans physical hardware build with power and RS485 wiring.", "tech_highlights": [ "ESP32Cam", "Home Assistant", "Relay + RS485" ], "created_at": "2026-10-27T22:31:05Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 14, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.4, "score_meta_tooling": 0.5, "score_tech_depth": 1.1, "score_demo": 0.8, "score_total": 3.8, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "High-impact domain", "+0.4" ] ], "meta": [ [ "Base", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "5+ window commits (14)", "+0.2" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ] ] }, "rank": 704, "is_new": true, "commits_delta": 14, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "52BaranHaydar/meta-hecatlon-project", "html_url": "https://github.com/52BaranHaydar/meta-hecatlon-project", "track": "Build for Your World", "domain": "Healthcare, Civic Tech & Sustainability", "summary": "Disaster support mobile app for emergency aid coordination (AFET DESTEK)", "readme_summary": "Flutter mobile app for disaster relief support with Android, iOS, Linux, macOS targets. Dart codebase in lib/ with Firebase config. No README details; appears focused on civic emergency assistance.", "tech_highlights": [ "Flutter + Dart", "Firebase", "Mobile Civic App" ], "created_at": "2026-10-28T12:38:16Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 9, "commits_before_window": 0, "prs_total": 3, "prs_merged": 3, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 1, "score_impact": 1.6, "score_meta_tooling": 0.5, "score_tech_depth": 1.3, "score_demo": 0.4, "score_total": 3.8, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "High-impact domain", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ] ], "meta": [ [ "Base", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "5+ window commits (9)", "+0.2" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "PR review workflow (3 PRs)", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ] ] }, "rank": 705, "is_new": false, "commits_delta": 6, "rank_delta": -335, "commits_delta_last_run": 0 }, { "full_name": "Jamespino20/helm-agent", "html_url": "https://github.com/Jamespino20/helm-agent", "track": "Build for Your World", "domain": "Business, Sales & Commerce", "summary": "Agent API for HELM POS and inventory management system", "readme_summary": "Next.js POS/inventory system with a dedicated agent API layer. TypeScript API with Vercel deployment exposing inventory operations to AI agents for the hackathon demo.", "tech_highlights": [ "Next.js POS", "Agent API", "Vercel + TypeScript" ], "created_at": "2026-10-27T01:52:17Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 6, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": true, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": true, "live_urls": [ "https://metahackathon-helm-agent.vercel.app" ], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.3, "score_meta_tooling": 0.5, "score_tech_depth": 0.8, "score_demo": 1.2, "score_total": 3.8, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "5+ window commits (6)", "+0.2" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Live web deployment", "+0.4" ] ] }, "rank": 706, "is_new": true, "commits_delta": 6, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "rafael-sanchezf/hush-iq", "html_url": "https://github.com/rafael-sanchezf/hush-iq", "track": "Build for Your World", "domain": "Business, Sales & Commerce", "summary": "NYC apartment noise score from city data, tuned to how you sleep.", "readme_summary": "Scores NYC apartment noise from 311 complaints, permits, licenses, transit and emergency data via API. Monorepo with apps and packages, live Vercel API. Uses Meta models to adjust scores from listings and write cited explanations.", "tech_highlights": [ "NYC Open Data", "Vercel API", "Meta Model Layer" ], "created_at": "2026-10-28T14:15:44Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 5, "commits_before_window": 0, "prs_total": 6, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": true, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": true, "live_urls": [ "https://hush-iq-api.vercel.app" ], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.3, "score_meta_tooling": 0.5, "score_tech_depth": 0.8, "score_demo": 1.2, "score_total": 3.8, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "5+ window commits (5)", "+0.2" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Live web deployment", "+0.4" ] ] }, "rank": 707, "is_new": false, "commits_delta": 0, "rank_delta": -379, "commits_delta_last_run": 0 }, { "full_name": "Lisovate/plomba", "html_url": "https://github.com/Lisovate/plomba", "track": "Build for Your World", "domain": "Multimodal Vision & Video (SAM / Vision)", "summary": "iPhone app that seals container condition with photos at every cargo handover.", "readme_summary": "Walk-around capture app for intermodal handovers with container number OCR validation. Uses Meta vision models to see damage, read labels, plus AR overlay of prior handover and Meta AI glasses capture. Concept stage with docs only.", "tech_highlights": [ "SAM Vision", "OCR + AR", "iOS + AI Glasses" ], "created_at": "2026-10-26T16:37:34Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 4, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": false, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": true, "has_eval_benchmarks": false, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.3, "score_meta_tooling": 1.8, "score_tech_depth": 0.3, "score_demo": 0.4, "score_total": 3.8, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ], [ "Open-weights / fine-tuning", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ] ] }, "rank": 708, "is_new": false, "commits_delta": 0, "rank_delta": -301, "commits_delta_last_run": 0 }, { "full_name": "sukritghosh886-hub/Sales-Analysis", "html_url": "https://github.com/sukritghosh886-hub/Sales-Analysis", "track": "Build for Your World", "domain": "Business, Sales & Commerce", "summary": "Simple web app to track sales, costs and profit or loss", "readme_summary": "Basic sale analytics app for tracking sales, costs and business profit. Built with web frontend, Firebase/Firestore config and Node server, deployed as a live static page.", "tech_highlights": [ "Firebase + Firestore", "Node Server", "Static Web App" ], "created_at": "2026-10-28T09:07:31Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 4, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": true, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": true, "live_urls": [ "https://sale-analytics-sukrit.pages.dev" ], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.5, "score_meta_tooling": 0.5, "score_tech_depth": 0.6, "score_demo": 1.2, "score_total": 3.8, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ] ], "meta": [ [ "Base", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Live web deployment", "+0.4" ] ] }, "rank": 709, "is_new": true, "commits_delta": 4, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "Ronisky-coder/Nia", "html_url": "https://github.com/Ronisky-coder/Nia", "track": "Push the Frontier", "domain": "Robotics, IoT & Manufacturing", "summary": "Deterministic safety gate and black box for AI-driven vehicles and robots", "readme_summary": "Turns Openwist vehicle/robot constitution into enforceable software. Muse models perceive and propose actions while an independent deterministic gate allows or blocks them with tamper-evident logging.", "tech_highlights": [ "Muse VLM", "Safety Gate Runtime", "Black Box Logging" ], "created_at": "2026-10-26T08:58:21Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 2, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": false, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.1, "score_meta_tooling": 0.8, "score_tech_depth": 0.3, "score_demo": 0.6, "score_total": 3.8, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "High-impact domain", "+0.4" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Muse Spark integration", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 710, "is_new": false, "commits_delta": 0, "rank_delta": -414, "commits_delta_last_run": 0 }, { "full_name": "kelleydonaldson/lunch-board-reader", "html_url": "https://github.com/kelleydonaldson/lunch-board-reader", "track": "Build for Your World", "domain": "Business, Sales & Commerce", "summary": "Human-approved system turning food-truck photo posts into lunch schedules", "readme_summary": "Reads food-truck schedule images into structured stops for Owensboro Market. Uses a vision model for input with never-guess flags, programmatic guardrails, approval queue, and provenance tracking.", "tech_highlights": [ "Vision Model Read", "Guardrails + Approval", "Provenance Tracking" ], "created_at": "2026-10-26T22:26:33Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 2, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": false, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.6, "score_meta_tooling": 1.3, "score_tech_depth": 0.3, "score_demo": 0.6, "score_total": 3.8, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 711, "is_new": false, "commits_delta": 0, "rank_delta": -414, "commits_delta_last_run": 0 }, { "full_name": "Ps23102004/patch-cross-examiner", "html_url": "https://github.com/Ps23102004/patch-cross-examiner", "track": "Push the Frontier", "domain": "Developer Tooling, Infra & Security", "summary": "Gates AI code fixes on counterexample tests to catch wrong-but-passing patches", "readme_summary": "Runner copies candidate patch, runs existing tests, then runs spec-derived counterexample tests. Validates counterexamples against known-correct fix to ensure verdict reliability. Built for Meta hackathon as AI code verification gate.", "tech_highlights": [ "Counterexample Testing", "Patch Verification", "Python Runner" ], "created_at": "2026-10-26T21:16:10Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 2, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": true, "has_tests": false, "has_src": false, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 2.2, "score_meta_tooling": 0.5, "score_tech_depth": 0.3, "score_demo": 0.8, "score_total": 3.8, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "High-impact domain", "+0.4" ], [ "Docker packaging", "+0.4" ] ], "meta": [ [ "Base", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ] ] }, "rank": 712, "is_new": false, "commits_delta": 0, "rank_delta": -277, "commits_delta_last_run": 0 }, { "full_name": "InsuJeong496/meisner-face-partner", "html_url": "https://github.com/InsuJeong496/meisner-face-partner", "track": "Build for Your World", "domain": "Gaming, Entertainment & Creative Media", "summary": "Korean-language Meisner repetition partner for solo actor rehearsal.", "readme_summary": "Prototype practice loop: observe partner, verbalize observation, hear repeat, respond. Stack/scripts under 02_Program and scripts, in development for hackathon. Meta model integration noted as in preparation, not yet documented.", "tech_highlights": [ "Korean Voice Practice", "Rehearsal Loop", "Hackathon Prototype" ], "created_at": "2026-10-26T16:48:13Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 1, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.5, "score_meta_tooling": 0.8, "score_tech_depth": 0.9, "score_demo": 0.6, "score_total": 3.8, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "General domain", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 713, "is_new": false, "commits_delta": 0, "rank_delta": -309, "commits_delta_last_run": 0 }, { "full_name": "mfreewill/Hackathon-Iynaa", "html_url": "https://github.com/mfreewill/Hackathon-Iynaa", "track": "Build for Your World", "domain": "Education & Knowledge Systems", "summary": "Arabic textbook page to Bloom-level questions workspace for teacher review only", "readme_summary": "Teacher-only local demo that takes one Arabic textbook page and proposes source sections. After source approval it drafts questions across six Bloom levels for explicit approval before preview. Built in Python as a standalone prototype around the Iynaa product idea.", "tech_highlights": [ "Python Local Demo", "Arabic Page-to-Lesson", "Bloom Levels Engine" ], "created_at": "2026-11-01T07:34:16Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 1, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.8, "score_meta_tooling": 0.5, "score_tech_depth": 0.9, "score_demo": 0.6, "score_total": 3.8, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 714, "is_new": true, "commits_delta": 1, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "saksham-45/showonce", "html_url": "https://github.com/saksham-45/showonce", "track": "Build for Your World", "domain": "Education & Knowledge Systems", "summary": "Turns a 60-second expert video into a live voice coach for physical skills", "readme_summary": "ShowOnce studies an expert clip and guides users with spoken corrections until steps check off. Stack is Meta Model API with Muse Spark reasoning, SAM 3.1 video segmentation, Muse Image and Muse Voice. Status is day-1 Learn pipeline in progress.", "tech_highlights": [ "Muse Spark 1.3", "SAM 3.1 Vision", "Muse Voice" ], "created_at": "2026-11-01T22:51:11Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 1, "commits_before_window": 0, "prs_total": 1, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": false, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.3, "score_meta_tooling": 1.8, "score_tech_depth": 0.3, "score_demo": 0.4, "score_total": 3.8, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ] ], "tech": [ [ "Base", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ] ] }, "rank": 715, "is_new": true, "commits_delta": 1, "rank_delta": 0, "commits_delta_last_run": 1 }, { "full_name": "trivnvdev-41/SEO-UGC-Meta-Hackathon-2026", "html_url": "https://github.com/trivnvdev-41/SEO-UGC-Meta-Hackathon-2026", "track": "Build for Your World", "domain": "Business, Sales & Commerce", "summary": "Turns TikTok/Reels/YouTube links into SEO articles with embeds.", "readme_summary": "Converts UGC video URLs into SEO-ready articles with JSON-LD and official embeds. Architecture is Next.js web, Node gateway with BullMQ, Python FastAPI media worker and Postgres. Uses AI STT for transcription and LLM for article generation.", "tech_highlights": [ "Next.js + FastAPI", "BullMQ + Postgres", "AI STT + LLM" ], "created_at": "2026-10-29T16:50:17Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 58, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": false, "has_ci": true, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.3, "score_meta_tooling": 0.5, "score_tech_depth": 1.1, "score_demo": 0.8, "score_total": 3.7, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (58)", "+0.6" ], [ "Automated CI workflow", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ] ] }, "rank": 716, "is_new": true, "commits_delta": 58, "rank_delta": 0, "commits_delta_last_run": 6 }, { "full_name": "Leonitex/hack-the-world", "html_url": "https://github.com/Leonitex/hack-the-world", "track": "Build for Your World", "domain": "Autonomous Agents & Workflow Automation", "summary": "Evidence-driven multimodal agent that diagnoses tech issues via observe-verify loop", "readme_summary": "Multimodal troubleshooting agent built around Observe-Hypothesize-Ask-Verify-Recommend loop. Collects symptoms, images and evidence to test hypotheses before recommending fixes. Python diagnostic_core with docs, examples and tests.", "tech_highlights": [ "Muse Spark", "Multimodal Diagnosis", "Python Agent" ], "created_at": "2026-10-27T20:55:50Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 20, "commits_before_window": 0, "prs_total": 1, "prs_merged": 1, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": false, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.4, "score_meta_tooling": 0.5, "score_tech_depth": 1.0, "score_demo": 0.8, "score_total": 3.7, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "High-impact domain", "+0.4" ] ], "meta": [ [ "Base", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (20)", "+0.4" ], [ "Automated test suite", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ] ] }, "rank": 717, "is_new": false, "commits_delta": 0, "rank_delta": -320, "commits_delta_last_run": 0 }, { "full_name": "frmquant/signaldesk", "html_url": "https://github.com/frmquant/signaldesk", "track": "Build for Your World", "domain": "Finance, Crypto & Web3", "summary": "Daily risk briefing agent that turns market signals into focus list.", "readme_summary": "SignalDesk is a single-page app where traders track signals and get a daily brief. Static HTML frontend with Muse Spark synthesis. Produces risk temperature, movers and watchlist as decision support only.", "tech_highlights": [ "Muse Spark", "Static HTML App", "Risk Briefing Agent" ], "created_at": "2026-10-26T17:08:56Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 18, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": false, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.3, "score_meta_tooling": 1.3, "score_tech_depth": 0.7, "score_demo": 0.4, "score_total": 3.7, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (18)", "+0.4" ] ], "demo": [ [ "Base", "+0.4" ] ] }, "rank": 718, "is_new": false, "commits_delta": 0, "rank_delta": -381, "commits_delta_last_run": 0 }, { "full_name": "leonidasrocky123-cell/edited-agent", "html_url": "https://github.com/leonidasrocky123-cell/edited-agent", "track": "Build for Your World", "domain": "Gaming, Entertainment & Creative Media", "summary": "Auto-cuts long videos into viral 9:16 clips with auto subtitles", "readme_summary": "Python app with cutter and meta_agent modules that selects highlights, reframes to vertical, adds subtitles and prepares social distribution. Built around Meta agent workflow for short-form clip creation.", "tech_highlights": [ "Meta Agent Workflow", "Auto Subtitles", "9:16 Auto Reframe" ], "created_at": "2026-10-28T14:48:55Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 13, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": false, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": false, "has_video_demo": true, "video_urls": [ "https://youtu.be/r85ZylOxQTs" ], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.2, "score_meta_tooling": 0.5, "score_tech_depth": 0.5, "score_demo": 1.5, "score_total": 3.7, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "General domain", "+0.2" ] ], "meta": [ [ "Base", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "5+ window commits (13)", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Video walkthrough", "+1.1" ] ] }, "rank": 719, "is_new": true, "commits_delta": 13, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "AliMora83/PartFix", "html_url": "https://github.com/AliMora83/PartFix", "track": "Push the Frontier", "domain": "Robotics, IoT & Manufacturing", "summary": "Converts a photo of a broken part into parametric CAD and print-ready STL.", "readme_summary": "Photo-to-CAD pipeline producing parametric models and STL for 3D printing. Python codebase in src with scripts and samples built during hackathon. Uses Meta Muse vision models for part recognition and geometry extraction.", "tech_highlights": [ "Muse Vision", "Parametric CAD", "Python + STL" ], "created_at": "2026-10-26T16:59:59Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 4, "commits_before_window": 0, "prs_total": 1, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": true, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.8, "score_meta_tooling": 0.5, "score_tech_depth": 0.6, "score_demo": 0.8, "score_total": 3.7, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "High-impact domain", "+0.4" ] ], "meta": [ [ "Base", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ] ] }, "rank": 720, "is_new": false, "commits_delta": 0, "rank_delta": -261, "commits_delta_last_run": 0 }, { "full_name": "tkinder/parish-record-reader", "html_url": "https://github.com/tkinder/parish-record-reader", "track": "Build for Your World", "domain": "Multimodal Vision & Video (SAM / Vision)", "summary": "Turns photos of old parish records into transcription and translation", "readme_summary": "Python tool that transcribes handwritten Spanish/Latin baptism, marriage and burial records. Translates to English and extracts names and dates into bilingual record. Uses Meta vision-language models for OCR.", "tech_highlights": [ "Python Vision OCR", "Transcription + Translation", "Meta Vision LLM" ], "created_at": "2026-10-26T17:17:10Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 3, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": false, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": true, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.6, "score_meta_tooling": 0.5, "score_tech_depth": 0.8, "score_demo": 0.8, "score_total": 3.7, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Eval & benchmark proof", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "Automated test suite", "+0.3" ], [ "Agent / eval harness", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ] ] }, "rank": 721, "is_new": false, "commits_delta": 0, "rank_delta": -281, "commits_delta_last_run": 0 }, { "full_name": "KARAN9846/mindloom-ai", "html_url": "https://github.com/KARAN9846/mindloom-ai", "track": "Build for Your World", "domain": "Education & Knowledge Systems", "summary": "Adaptive learning app with personalized lessons and smart assessments", "readme_summary": "Next.js adaptive learning platform with interactive experiments and assessments. Stack is Next.js App Router, Geist font, tests and lib modules. Uses Meta AI / Muse models for personalization and tutoring.", "tech_highlights": [ "Next.js App Router", "Adaptive Learning", "Muse Models" ], "created_at": "2026-10-29T05:27:41Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 3, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.5, "score_meta_tooling": 0.5, "score_tech_depth": 0.9, "score_demo": 0.8, "score_total": 3.7, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ] ], "meta": [ [ "Base", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ] ] }, "rank": 722, "is_new": false, "commits_delta": 0, "rank_delta": -313, "commits_delta_last_run": 0 }, { "full_name": "bgrubbs1/lantern-room-meta-vr", "html_url": "https://github.com/bgrubbs1/lantern-room-meta-vr", "track": "Build for Your World", "domain": "Gaming, Entertainment & Creative Media", "summary": "Seated hands-first WebXR VR puzzle about waking a sleeping lantern", "readme_summary": "The Lantern Room is a quiet WebXR puzzle built with Meta Immersive Web SDK for VR Start 2026. It offers a hands-first observatory table with lantern, orrery and dial puzzles and no menus or locomotion.", "tech_highlights": [ "Meta IWSDK + WebXR", "Three.js + TypeScript", "VR Puzzle Game" ], "created_at": "2026-10-27T17:13:33Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 3, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.7, "score_meta_tooling": 0.5, "score_tech_depth": 0.9, "score_demo": 0.6, "score_total": 3.7, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "General domain", "+0.2" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 723, "is_new": true, "commits_delta": 3, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "jai-nayani/BinBuild", "html_url": "https://github.com/jai-nayani/BinBuild", "track": "Build for Your World", "domain": "Gaming, Entertainment & Creative Media", "summary": "Scans loose LEGO bins and creates build guides from owned pieces only", "readme_summary": "Phone photo inventory via Meta SAM 3.1, user review loop, then inventory-constrained BrickGPT generation with step-by-step booklet. Built with SAM 3.1, Muse Spark, limited to 8 brick types for generation. Fan project, not LEGO affiliated.", "tech_highlights": [ "SAM 3.1 Vision", "Muse Spark", "BrickGPT + Inventory" ], "created_at": "2026-10-26T16:02:45Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 2, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": true, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.2, "score_meta_tooling": 1.1, "score_tech_depth": 0.6, "score_demo": 0.8, "score_total": 3.7, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "General domain", "+0.2" ] ], "meta": [ [ "Base", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ] ] }, "rank": 724, "is_new": false, "commits_delta": 0, "rank_delta": -351, "commits_delta_last_run": 0 }, { "full_name": "wd809/noa-guardian", "html_url": "https://github.com/wd809/noa-guardian", "track": "Build for Your World", "domain": "Healthcare, Civic Tech & Sustainability", "summary": "Smart-glasses safety assistant with official alerts, legal answers and vision awareness", "readme_summary": "NOA Guardian provides official-source alerts from NWS, USGS and NASA EONET with verified all-clear logic. It uses Angular web, NestJS dock and shared TypeScript contracts with Leaflet Esri maps. Citizen answers are extractive with citations and Awareness analyzes images via /see.", "tech_highlights": [ "Angular + NestJS", "Leaflet Esri Maps", "NWS USGS EONET" ], "created_at": "2026-10-26T22:03:43Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 2, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.6, "score_meta_tooling": 0.8, "score_tech_depth": 0.9, "score_demo": 0.4, "score_total": 3.7, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "High-impact domain", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ] ], "meta": [ [ "Base", "+0.5" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ] ] }, "rank": 725, "is_new": false, "commits_delta": 0, "rank_delta": -681, "commits_delta_last_run": 0 }, { "full_name": "Hyunjin-Cho/little-world-book", "html_url": "https://github.com/Hyunjin-Cho/little-world-book", "track": "Build for Your World", "domain": "Education & Knowledge Systems", "summary": "Interactive Three.js 3D pop-up book that teaches math to ages 7-8 through touch", "readme_summary": "Early-stage project scaffolding repo with docs only, no runnable app yet. Plans Three.js book with countable objects for quantity learning, starting with math. Intends to use Meta Model API and Muse Spark for request understanding, keys kept server-side.", "tech_highlights": [ "Three.js 3D", "Muse Spark", "Meta Model API" ], "created_at": "2026-10-26T13:16:04Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 1, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": false, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": true, "live_urls": [ "https://iamtechartist.github.io/every-joule-lesson1/" ], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.3, "score_meta_tooling": 1.3, "score_tech_depth": 0.3, "score_demo": 0.8, "score_total": 3.7, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Live web deployment", "+0.4" ] ] }, "rank": 726, "is_new": false, "commits_delta": 0, "rank_delta": -336, "commits_delta_last_run": 0 }, { "full_name": "ycheng87/chengmo-websites-pipeline", "html_url": "https://github.com/ycheng87/chengmo-websites-pipeline", "track": "Build for Your World", "domain": "Business, Sales & Commerce", "summary": "Agent pipeline that researches fictional shops then builds demo sites and outreach drafts", "readme_summary": "Async-generator pipeline: research, demo site, outreach, follow-up plus scoring with JSONL logs in runs/. Uses fictional demo brands only for merchant outreach testing. Integrates LLM for copy and DuckDuckGo for research with Python CLI.", "tech_highlights": [ "Python Agent Pipeline", "LLM + DDG Search", "JSONL Run Logs" ], "created_at": "2026-10-27T09:51:15Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 1, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": false, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.6, "score_meta_tooling": 0.8, "score_tech_depth": 0.3, "score_demo": 1.0, "score_total": 3.7, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Muse Spark integration", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 727, "is_new": true, "commits_delta": 1, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "mbyo2/doc0clock-ai-triage", "html_url": "https://github.com/mbyo2/doc0clock-ai-triage", "track": "Build for Your World", "domain": "Healthcare, Civic Tech & Sustainability", "summary": "Rules-first symptom triage assistant that routes Zambian telehealth patients to right care level", "readme_summary": "Live at Doc'O Clock /triage, it takes symptom chips, free text, severity and risk factors through TriageAssistant.tsx. Rules engine gates urgency with a Meta Model API step for refinement and booking. Built with React frontend and Supabase backend on a live telehealth platform.", "tech_highlights": [ "Meta Model API", "React + Supabase", "Rules-first Triage" ], "created_at": "2026-10-30T20:58:13Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 1, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": true, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.7, "score_meta_tooling": 1.0, "score_tech_depth": 0.6, "score_demo": 0.4, "score_total": 3.7, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "High-impact domain", "+0.4" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ] ] }, "rank": 728, "is_new": true, "commits_delta": 1, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "A3dSquare/Meta-2026-Hackathon", "html_url": "https://github.com/A3dSquare/Meta-2026-Hackathon", "track": "Build for Your World", "domain": "Multimodal Vision & Video (SAM / Vision)", "summary": "Vision detection tool that captures images and identifies on-screen events", "readme_summary": "Vision detection tool that captures images and identifies on-screen events", "tech_highlights": [], "created_at": "2026-10-26T08:24:34Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 81, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": false, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.5, "score_meta_tooling": 0.5, "score_tech_depth": 1.2, "score_demo": 0.4, "score_total": 3.6, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ] ], "meta": [ [ "Base", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (81)", "+0.6" ], [ "Automated test suite", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ] ] }, "rank": 729, "is_new": false, "commits_delta": 20, "rank_delta": -396, "commits_delta_last_run": 0 }, { "full_name": "asub927/meta-ai-hackathon", "html_url": "https://github.com/asub927/meta-ai-hackathon", "track": "Build for Your World", "domain": "Education & Knowledge Systems", "summary": "Planned iPad-first Socratic math app where mascots act out story consequences.", "readme_summary": "Planning-only repo for an open-source grade-2 math app with hint ladder and on-device progress, no backend. Defines web-first then native SwiftUI iPad build covering NCDPI curriculum. No implementation or Meta model integration yet.", "tech_highlights": [ "SwiftUI iPad Plan", "Socratic Tutor Design", "On-Device Privacy" ], "created_at": "2026-10-29T02:52:20Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 33, "commits_before_window": 0, "prs_total": 5, "prs_merged": 4, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": true, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.5, "score_meta_tooling": 0.5, "score_tech_depth": 1.2, "score_demo": 0.4, "score_total": 3.6, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ] ], "meta": [ [ "Base", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (33)", "+0.4" ], [ "Modular src/ architecture", "+0.3" ], [ "PR review workflow (4 PRs)", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ] ] }, "rank": 730, "is_new": false, "commits_delta": 27, "rank_delta": -348, "commits_delta_last_run": 0 }, { "full_name": "zavora-ai/agentrix-website", "html_url": "https://github.com/zavora-ai/agentrix-website", "track": "Build for Your World", "domain": "Business, Sales & Commerce", "summary": "Agentic Website 4.0 that answers leads and handles business tasks autonomously", "readme_summary": "Replaces brochure sites with an agent built on ADK-Rust and Meta Muse models. Handles lead response, business workflows and data tasks autonomously. Includes concept visuals, hosted site and showcase video.", "tech_highlights": [ "Muse Models", "ADK-Rust", "Agentic Website" ], "created_at": "2026-10-30T04:52:35Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 28, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": false, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 1, "score_impact": 1.8, "score_meta_tooling": 0.5, "score_tech_depth": 0.7, "score_demo": 0.6, "score_total": 3.6, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (28)", "+0.4" ] ], "demo": [ [ "Base", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 731, "is_new": true, "commits_delta": 28, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "abzy128/kazakh-rpg", "html_url": "https://github.com/abzy128/kazakh-rpg", "track": "Build for Your World", "domain": "Gaming, Entertainment & Creative Media", "summary": "Voice-driven role-play game that teaches Kazakh culture and values", "readme_summary": "Interactive voice RPG for learning Kazakh culture built with TanStack Start, Vite and Tailwind. Uses Meta models for dialogue and voice interaction. Runs with Bun install and dev build.", "tech_highlights": [ "TanStack Start + Vite", "Tailwind CSS", "Meta Voice Models" ], "created_at": "2026-10-27T12:32:23Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 3, "commits_before_window": 0, "prs_total": 1, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": true, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.7, "score_meta_tooling": 0.5, "score_tech_depth": 0.6, "score_demo": 0.8, "score_total": 3.6, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "General domain", "+0.2" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ] ] }, "rank": 732, "is_new": false, "commits_delta": 0, "rank_delta": -367, "commits_delta_last_run": 0 }, { "full_name": "ravindrakumavat/GHOSTLINK", "html_url": "https://github.com/ravindrakumavat/GHOSTLINK", "track": "Build for Your World", "domain": "Healthcare, Civic Tech & Sustainability", "summary": "Offline-first SOS relay over BLE to backend when internet returns.", "readme_summary": "Prototype for emergency SOS creation, local outbox storage, and manual BLE peer relay. Uses a mobile client for BLE scan/transfer and a FastAPI backend for submission. No explicit Meta AI / Muse model usage documented.", "tech_highlights": [ "BLE Offline Relay", "FastAPI Backend", "Mobile + Local Outbox" ], "created_at": "2026-10-27T17:49:52Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 1, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": true, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 1, "score_impact": 1.7, "score_meta_tooling": 0.5, "score_tech_depth": 0.6, "score_demo": 0.8, "score_total": 3.6, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "High-impact domain", "+0.4" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ] ] }, "rank": 733, "is_new": true, "commits_delta": 1, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "buildwithdesi/vibeaudit-2-demo-app", "html_url": "https://github.com/buildwithdesi/vibeaudit-2-demo-app", "track": "Push the Frontier", "domain": "Developer Tooling, Infra & Security", "summary": "Intentionally vulnerable Express app to demo security scanner.", "readme_summary": "Express demo with five planted flaws: secrets, SQL injection, authz, command injection, traversal/SSRF. Companion before-state for Vibe Audit 2.0 scanner. No Meta AI model calls in this target app itself.", "tech_highlights": [ "Express.js Vulnerable", "5 Vuln Classes", "Scanner Test Target" ], "created_at": "2026-10-27T23:18:12Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 1, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.8, "score_meta_tooling": 0.5, "score_tech_depth": 0.9, "score_demo": 0.4, "score_total": 3.6, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "High-impact domain", "+0.4" ] ], "meta": [ [ "Base", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ] ] }, "rank": 734, "is_new": false, "commits_delta": 0, "rank_delta": -313, "commits_delta_last_run": 0 }, { "full_name": "labsbytir/harvy", "html_url": "https://github.com/labsbytir/harvy", "track": "Build for Your World", "domain": "Business, Sales & Commerce", "summary": "Tenant-scoped SaaS for source-grounded intelligence, BI, civic events and ops handoffs", "readme_summary": "Harvy is a web SaaS for source-grounded intelligence with shared ontology, HQL query contract and HarvyDex UUIDs. Stack is Better Auth, tenant-scoped API, Drizzle + D1 analytics, Cloudflare Worker/R2 and n8n automation templates. Muse model usage is not detailed in the excerpt.", "tech_highlights": [ "Better Auth + Drizzle", "Cloudflare D1 + R2", "n8n Automation" ], "created_at": "2026-10-28T07:14:17Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 51, "commits_before_window": 0, "prs_total": 2, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": false, "has_ci": true, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.5, "score_meta_tooling": 0.5, "score_tech_depth": 1.1, "score_demo": 0.4, "score_total": 3.5, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ] ], "meta": [ [ "Base", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (51)", "+0.6" ], [ "Automated CI workflow", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ] ] }, "rank": 735, "is_new": true, "commits_delta": 51, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "mzaks/Pixalorien", "html_url": "https://github.com/mzaks/Pixalorien", "track": "Build for Your World", "domain": "Gaming, Entertainment & Creative Media", "summary": "Single-player falling-sand game with pausable and rewindable time", "readme_summary": "Falling-sand adventure in ent-lang where three Pixaloriens explore vault under desert planet. Custom cellular automaton on 2048x1024 grid with deterministic simulation. Assets partly made with Meta Muse model.", "tech_highlights": [ "ent-lang Engine", "Cellular Automaton", "Muse Assets" ], "created_at": "2026-10-30T05:08:59Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 42, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": false, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.7, "score_meta_tooling": 0.5, "score_tech_depth": 0.7, "score_demo": 0.6, "score_total": 3.5, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "General domain", "+0.2" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (42)", "+0.4" ] ], "demo": [ [ "Base", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 736, "is_new": true, "commits_delta": 42, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "bborel-dev/drawlab", "html_url": "https://github.com/bborel-dev/drawlab", "track": "Build for Your World", "domain": "Gaming, Entertainment & Creative Media", "summary": "Five AI agents redraw any image live stroke-by-stroke as layered SVG", "readme_summary": "AI drawing studio that converts uploaded images into clean layered SVG via five cooperating agents with live stroke rendering. Backend + frontend stack with samples and scripts. Built with Meta Muse models for Meta Global AI Developer Hackathon 2026.", "tech_highlights": [ "Meta Muse", "Multi-Agent SVG", "Live Stroke Rendering" ], "created_at": "2026-10-26T16:32:11Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 26, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": true, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.2, "score_meta_tooling": 0.5, "score_tech_depth": 1.0, "score_demo": 0.8, "score_total": 3.5, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "General domain", "+0.2" ] ], "meta": [ [ "Base", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (26)", "+0.4" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ] ] }, "rank": 737, "is_new": false, "commits_delta": 5, "rank_delta": -305, "commits_delta_last_run": 0 }, { "full_name": "foreverest/meta-hackathon-finger-pods", "html_url": "https://github.com/foreverest/meta-hackathon-finger-pods", "track": "Push the Frontier", "domain": "Robotics, IoT & Manufacturing", "summary": "Wearable finger clips for typing on any surface with one hand", "readme_summary": "One-hand wearable text input prototype with finger-clip firmware and host software. Validates clicky wearable typing for glasses-era computing; includes firmware, host code, and feasibility worklog.", "tech_highlights": [ "Embedded Firmware", "Wearable Sensors", "Host Decoder" ], "created_at": "2026-10-27T03:35:08Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 14, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": false, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.8, "score_meta_tooling": 0.5, "score_tech_depth": 0.8, "score_demo": 0.4, "score_total": 3.5, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "High-impact domain", "+0.4" ] ], "meta": [ [ "Base", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "5+ window commits (14)", "+0.2" ], [ "Automated test suite", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ] ] }, "rank": 738, "is_new": true, "commits_delta": 14, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "COMPIZMX/aula-raiz", "html_url": "https://github.com/COMPIZMX/aula-raiz", "track": "Build for Your World", "domain": "Education & Knowledge Systems", "summary": "Turns lessons into short reels in Spanish and Indigenous languages", "readme_summary": "Generates original scripts via Muse Spark through Meta Model API, plus Aztec-inspired scenes, narration and music. Supports Maya, Huichol, Nahuatl, Zapotec for classroom and language learning.", "tech_highlights": [ "Muse Spark 1.3", "Multilingual Narration", "Reel Video Pipeline" ], "created_at": "2026-11-01T01:53:55Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 13, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": false, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.3, "score_meta_tooling": 1.3, "score_tech_depth": 0.5, "score_demo": 0.4, "score_total": 3.5, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "5+ window commits (13)", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ] ] }, "rank": 739, "is_new": true, "commits_delta": 13, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "arnavjhajharia/meta-ai-hackathon", "html_url": "https://github.com/arnavjhajharia/meta-ai-hackathon", "track": "Build for Your World", "domain": "General & Emerging Applications", "summary": "Hackathon prototype with minimal metadata using Meta models.", "readme_summary": "Hackathon prototype with minimal metadata using Meta models.", "tech_highlights": [], "created_at": "2026-10-25T22:49:27Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 8, "commits_before_window": 1, "prs_total": 0, "prs_merged": 0, "is_preexisting": true, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.4, "score_meta_tooling": 0.2, "score_tech_depth": 1.1, "score_demo": 0.8, "score_total": 3.5, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "General domain", "+0.2" ], [ "Multi-module scope (>10 files)", "+0.2" ] ], "meta": [ [ "Base", "+0.5" ], [ "Non-Meta runtime SDK only", "-0.6" ] ], "tech": [ [ "Base", "+0.3" ], [ "5+ window commits (8)", "+0.2" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ] ] }, "rank": 740, "is_new": false, "commits_delta": 0, "rank_delta": -359, "commits_delta_last_run": 0 }, { "full_name": "jeffrey840/QuickAisle", "html_url": "https://github.com/jeffrey840/QuickAisle", "track": "Build for Your World", "domain": "Business, Sales & Commerce", "summary": "Grocery shopping assistant for fast aisle navigation and checkout", "readme_summary": "Monorepo with apps, server, packages, eval and data for a retail shopping workflow. TypeScript project with handoff plan and eval harness. Built for Meta hackathon, likely uses Muse models for shopping assistance.", "tech_highlights": [ "TypeScript Monorepo", "Node + Eval Harness", "Muse Spark" ], "created_at": "2026-10-26T19:32:30Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 3, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": true, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": true, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.8, "score_meta_tooling": 0.5, "score_tech_depth": 0.8, "score_demo": 0.4, "score_total": 3.5, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Eval & benchmark proof", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ] ], "meta": [ [ "Base", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Agent / eval harness", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ] ] }, "rank": 741, "is_new": false, "commits_delta": 2, "rank_delta": -257, "commits_delta_last_run": 0 }, { "full_name": "gevalinho/codearchaeologist-ai", "html_url": "https://github.com/gevalinho/codearchaeologist-ai", "track": "Push the Frontier", "domain": "Developer Tooling, Infra & Security", "summary": "Autonomous agent that uncovers legacy business logic and verifies it with tests", "readme_summary": "Investigates legacy codebases to reconstruct undocumented business rules and dependencies. Uses autonomous agent workflows that generate executable tests to verify discoveries. Built with Meta AI models for the 2026 hackathon.", "tech_highlights": [ "Autonomous Code Agents", "Test Verification", "Muse Models" ], "created_at": "2026-10-26T23:21:36Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 2, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": false, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.8, "score_meta_tooling": 1.0, "score_tech_depth": 0.3, "score_demo": 0.4, "score_total": 3.5, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "High-impact domain", "+0.4" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ] ] }, "rank": 742, "is_new": false, "commits_delta": 0, "rank_delta": -312, "commits_delta_last_run": 0 }, { "full_name": "djangohermoso/paper-to-grades", "html_url": "https://github.com/djangohermoso/paper-to-grades", "track": "Build for Your World", "domain": "Education & Knowledge Systems", "summary": "Turns photos of handwritten class records into checked DepEd gradebooks", "readme_summary": "Provides grading engine with weighted grades, DepEd transmutation, error checks, review UI with photo beside editable grid and CSV export. Built with Python, FastAPI/Uvicorn. Meta model photo reading planned, currently uses stand-in reader.", "tech_highlights": [ "FastAPI + Uvicorn", "DepEd Grading Engine", "Planned Meta Vision" ], "created_at": "2026-10-28T04:22:26Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 2, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.3, "score_meta_tooling": 0.5, "score_tech_depth": 0.9, "score_demo": 0.8, "score_total": 3.5, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ] ] }, "rank": 743, "is_new": false, "commits_delta": 0, "rank_delta": -330, "commits_delta_last_run": 0 }, { "full_name": "tprsmail-cell/suzarchi-meta-hackathon-2026", "html_url": "https://github.com/tprsmail-cell/suzarchi-meta-hackathon-2026", "track": "Build for Your World", "domain": "Healthcare, Civic Tech & Sustainability", "summary": "Finds reuse ideas for surplus textile materials from business inputs", "readme_summary": "Explores AI-assisted discovery of reuse opportunities for textile surplus like fabric, yarn and offcuts. Uses Meta models plus rule-based compatibility checks. Early prototype scope with material input and opportunity workflow, proposed as Push the Frontier.", "tech_highlights": [ "Muse Models", "Rule-Based Checks", "Material Workflow" ], "created_at": "2026-10-26T16:04:34Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 2, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": false, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.4, "score_meta_tooling": 1.0, "score_tech_depth": 0.3, "score_demo": 0.8, "score_total": 3.5, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "High-impact domain", "+0.4" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ] ] }, "rank": 744, "is_new": false, "commits_delta": 0, "rank_delta": -378, "commits_delta_last_run": 0 }, { "full_name": "asinadarsh/arclor-meta-hackathon", "html_url": "https://github.com/asinadarsh/arclor-meta-hackathon", "track": "Build for Your World", "domain": "Gaming, Entertainment & Creative Media", "summary": "Turns a website into an editable launch-ready motion-graphics product video", "readme_summary": "Standalone hackathon layer on top of Arclor product for script and scene generation. Uses Muse Spark via Meta Model API for product-grounded scripts and SAM 3.1 for visual scene understanding. Outputs 1080p captioned video with Studio editor and analytics.", "tech_highlights": [ "Muse Spark 1.3", "SAM 3.1 Vision", "Video + Studio Editor" ], "created_at": "2026-10-26T20:33:37Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 1, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": false, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.2, "score_meta_tooling": 1.6, "score_tech_depth": 0.3, "score_demo": 0.4, "score_total": 3.5, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "General domain", "+0.2" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ] ] }, "rank": 745, "is_new": false, "commits_delta": 0, "rank_delta": -390, "commits_delta_last_run": 0 }, { "full_name": "RohanJosephGeorge/ReTracer_AI", "html_url": "https://github.com/RohanJosephGeorge/ReTracer_AI", "track": "Build for Your World", "domain": "Multimodal Vision & Video (SAM / Vision)", "summary": "Image forensics toolkit for screening faces, quality checks and SAM segmentation.", "readme_summary": "Streamlit app with backend modules for face screening, file sanitizing, image quality and spatial reasoning. Uses SAM segmentation for region analysis. File tree suggests Python vision pipeline with generated image assets.", "tech_highlights": [ "SAM Segmentation", "Streamlit + Python", "Face Screening" ], "created_at": "2026-10-27T07:30:48Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 29, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": false, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.5, "score_meta_tooling": 0.5, "score_tech_depth": 1.0, "score_demo": 0.4, "score_total": 3.4, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ] ], "meta": [ [ "Base", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (29)", "+0.4" ], [ "Automated test suite", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ] ] }, "rank": 746, "is_new": true, "commits_delta": 29, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "belleflykids/bellefly-kids-story-builder", "html_url": "https://github.com/belleflykids/bellefly-kids-story-builder", "track": "Build for Your World", "domain": "Education & Knowledge Systems", "summary": "Parent-led bedtime story builder with Bellefly Kids characters", "readme_summary": "Static index.html app with image assets and an ai-agent folder for parent-led bedtime stories. Simple frontend demo with no build system. Uses Meta AI models to generate safe stories in the Bellefly Kids world.", "tech_highlights": [ "Static HTML + JS", "Muse Spark", "Parent-Led Safety" ], "created_at": "2026-10-28T18:30:17Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 22, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": false, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.5, "score_meta_tooling": 0.5, "score_tech_depth": 1.0, "score_demo": 0.4, "score_total": 3.4, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ] ], "meta": [ [ "Base", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (22)", "+0.4" ], [ "Automated test suite", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ] ] }, "rank": 747, "is_new": false, "commits_delta": 19, "rank_delta": -283, "commits_delta_last_run": 0 }, { "full_name": "igoreduardoai/closingcount", "html_url": "https://github.com/igoreduardoai/closingcount", "track": "Build for Your World", "domain": "Healthcare, Civic Tech & Sustainability", "summary": "Offline vision ledger for reconciling physical item counts.", "readme_summary": "Deterministic ledger tracks baseline to closing counts; SAM 3 vision counts items per class/zone from top-down images. Demo simulates surgical counts with household objects. Built offline-first for hackathon research.", "tech_highlights": [ "SAM 3 Vision", "Deterministic Ledger", "Offline Agent" ], "created_at": "2026-10-26T18:43:40Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 1, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": false, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": true, "has_eval_benchmarks": false, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.4, "score_meta_tooling": 1.3, "score_tech_depth": 0.3, "score_demo": 0.4, "score_total": 3.4, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "High-impact domain", "+0.4" ] ], "meta": [ [ "Base", "+0.5" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "Open-weights / fine-tuning", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ] ] }, "rank": 748, "is_new": false, "commits_delta": 0, "rank_delta": -303, "commits_delta_last_run": 0 }, { "full_name": "lizecaint/PhotoTidy", "html_url": "https://github.com/lizecaint/PhotoTidy", "track": "Build for Your World", "domain": "Multimodal Vision & Video (SAM / Vision)", "summary": "iOS agent that flags clearable photos with evidence before you approve", "readme_summary": "Native iOS app listing screenshots and recents with size and metadata for cleanup suggestions. Planned Apple Vision OCR plus Muse Spark agent loop for structured verdicts with evidence, never auto-deletes.", "tech_highlights": [ "iOS + Swift", "Apple Vision OCR", "Muse Spark Agent" ], "created_at": "2026-11-01T20:32:48Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 1, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.3, "score_meta_tooling": 0.8, "score_tech_depth": 0.9, "score_demo": 0.4, "score_total": 3.4, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Muse Spark integration", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ] ] }, "rank": 749, "is_new": true, "commits_delta": 1, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "samirrhashimov/meta-ai-hackathon-2026", "html_url": "https://github.com/samirrhashimov/meta-ai-hackathon-2026", "track": "Build for Your World", "domain": "General & Emerging Applications", "summary": "Web app with frontend and backend built for hackathon.", "readme_summary": "Web app with frontend and backend built for hackathon.", "tech_highlights": [], "created_at": "2026-10-27T11:55:55Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 35, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": true, "has_ci": true, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.2, "score_meta_tooling": 0.5, "score_tech_depth": 1.2, "score_demo": 0.4, "score_total": 3.3, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "General domain", "+0.2" ] ], "meta": [ [ "Base", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (35)", "+0.4" ], [ "Modular src/ architecture", "+0.3" ], [ "Automated CI workflow", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ] ] }, "rank": 750, "is_new": false, "commits_delta": 25, "rank_delta": -326, "commits_delta_last_run": 0 }, { "full_name": "RohanJosephGeorge/Spatial_Memory_Geoguesser", "html_url": "https://github.com/RohanJosephGeorge/Spatial_Memory_Geoguesser", "track": "Build for Your World", "domain": "Gaming, Entertainment & Creative Media", "summary": "Photo-based GeoGuessr clone that guesses locations using spatial reasoning", "readme_summary": "Streamlit app with Python backend for location guessing gameplay. Stack includes app.py, backend.py, sam_segmentation.py, spatial_reasoning.py and image quality screening. Uses SAM segmentation and Muse models for spatial analysis.", "tech_highlights": [ "SAM Segmentation", "Muse Spark", "Streamlit + Python" ], "created_at": "2026-10-27T07:30:48Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 29, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": false, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.4, "score_meta_tooling": 0.5, "score_tech_depth": 1.0, "score_demo": 0.4, "score_total": 3.3, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "General domain", "+0.2" ], [ "Multi-module scope (>10 files)", "+0.2" ] ], "meta": [ [ "Base", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (29)", "+0.4" ], [ "Automated test suite", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ] ] }, "rank": 751, "is_new": false, "commits_delta": 7, "rank_delta": -393, "commits_delta_last_run": 0 }, { "full_name": "alihassan1437/helpious-hackathon-ai", "html_url": "https://github.com/alihassan1437/helpious-hackathon-ai", "track": "Build for Your World", "domain": "Business, Sales & Commerce", "summary": "AI gateway for tradie marketplace with photo quotes, drafts and voice input", "readme_summary": "Adds /api/ai gateway on top of pre-existing Helpious marketplace with Snap-to-Quote briefs, safety card, lead briefs and quote drafts. Hackathon-only Node code documents pre-existing vs new work separation.", "tech_highlights": [ "Meta Muse Models", "AI Gateway API", "Snap-to-Quote" ], "created_at": "2026-10-26T17:15:52Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 8, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.3, "score_meta_tooling": 0.5, "score_tech_depth": 1.1, "score_demo": 0.4, "score_total": 3.3, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "5+ window commits (8)", "+0.2" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ] ] }, "rank": 752, "is_new": false, "commits_delta": 5, "rank_delta": -342, "commits_delta_last_run": 0 }, { "full_name": "bolouvipf/medelor", "html_url": "https://github.com/bolouvipf/medelor", "track": "Build for Your World", "domain": "Voice, Speech & Audio AI", "summary": "Dubbing tool giving each on-screen character its own translated voice", "readme_summary": "Separates speakers in a short clip, translates each character's lines, and synthesizes a distinct voice per character. Built during the hackathon with no pre-existing code. Uses Meta open-weight models via Baseten compared on the same translation task.", "tech_highlights": [ "Meta Open-Weight Models", "Baseten Inference", "Speaker Separation" ], "created_at": "2026-10-27T03:30:48Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 6, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": false, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.5, "score_meta_tooling": 0.5, "score_tech_depth": 0.5, "score_demo": 0.8, "score_total": 3.3, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ] ], "meta": [ [ "Base", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "5+ window commits (6)", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ] ] }, "rank": 753, "is_new": false, "commits_delta": 0, "rank_delta": -326, "commits_delta_last_run": 0 }, { "full_name": "yusuffolufemi532-glitch/aone-bp", "html_url": "https://github.com/yusuffolufemi532-glitch/aone-bp", "track": "Build for Your World", "domain": "Business, Sales & Commerce", "summary": "WhatsApp assistant that drafts salon replies for owner approval.", "readme_summary": "WhatsApp business partner for Nigerian salons and vendors enforcing price floors in code. Node.js src with data, scripts and tests, replies gated on owner approval. Built solo for hackathon Indie track with owner-tone replies.", "tech_highlights": [ "WhatsApp Business", "Node.js", "Rule Enforcement" ], "created_at": "2026-10-27T18:15:45Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 5, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.3, "score_meta_tooling": 0.5, "score_tech_depth": 1.1, "score_demo": 0.4, "score_total": 3.3, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "5+ window commits (5)", "+0.2" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ] ] }, "rank": 754, "is_new": false, "commits_delta": 2, "rank_delta": -343, "commits_delta_last_run": 0 }, { "full_name": "xDes1107/Tempo", "html_url": "https://github.com/xDes1107/Tempo", "track": "Build for Your World", "domain": "Business, Sales & Commerce", "summary": "Company data app with backend and structured company JSON modeling", "readme_summary": "Appears to be a business-focused web app with Node backend, data layer and index.html frontend. Repo includes architecture docs and company JSON test harness. Likely uses Meta AI for company data processing.", "tech_highlights": [ "Node.js Backend", "Company JSON", "Meta AI" ], "created_at": "2026-10-30T23:38:42Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 3, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.5, "score_meta_tooling": 0.5, "score_tech_depth": 0.9, "score_demo": 0.4, "score_total": 3.3, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ] ], "meta": [ [ "Base", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ] ] }, "rank": 755, "is_new": true, "commits_delta": 3, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "Durreshehwar15/TraceMind", "html_url": "https://github.com/Durreshehwar15/TraceMind", "track": "Push the Frontier", "domain": "Developer Tooling, Infra & Security", "summary": "", "readme_summary": "", "tech_highlights": [], "created_at": "2026-10-27T05:10:10Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 1, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": true, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.8, "score_meta_tooling": 0.5, "score_tech_depth": 0.6, "score_demo": 0.4, "score_total": 3.3, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "High-impact domain", "+0.4" ] ], "meta": [ [ "Base", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ] ] }, "rank": 756, "is_new": false, "commits_delta": 0, "rank_delta": -367, "commits_delta_last_run": 0 }, { "full_name": "mataindustries/thing-mania", "html_url": "https://github.com/mataindustries/thing-mania", "track": "Build for Your World", "domain": "Gaming, Entertainment & Creative Media", "summary": "29-second browser arcade game that remixes one everyday object across three universes", "readme_summary": "THING//MANIA v0.2 is pure HTML, CSS, Canvas and Web Audio with optional local photo, no servers or packages. Opens via index.html with instant play and no accounts. Built fresh for hackathon with no Meta AI / Muse model calls.", "tech_highlights": [ "HTML Canvas", "Web Audio API", "Static No-backend" ], "created_at": "2026-10-27T21:30:53Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 1, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": false, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.5, "score_meta_tooling": 1.1, "score_tech_depth": 0.3, "score_demo": 0.4, "score_total": 3.3, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "General domain", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ] ] }, "rank": 757, "is_new": false, "commits_delta": 0, "rank_delta": -390, "commits_delta_last_run": 0 }, { "full_name": "lunarcit0/Meta-AI-Hackathon", "html_url": "https://github.com/lunarcit0/Meta-AI-Hackathon", "track": "Build for Your World", "domain": "Gaming, Entertainment & Creative Media", "summary": "2D space game where rumors spread and NPCs can lie", "readme_summary": "HEARSAY is a 2D Python space exploration game built from rumors. Engine tracks truth while local Llama via Ollama styles NPC dialogue. Run with Python 3.10, optional llama3.2 models.", "tech_highlights": [ "Python game", "Llama 3.2 via Ollama", "NPC dialogue AI" ], "created_at": "2026-10-28T20:37:00Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 1, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": false, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": true, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.5, "score_meta_tooling": 0.5, "score_tech_depth": 0.5, "score_demo": 0.8, "score_total": 3.3, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "General domain", "+0.2" ], [ "Eval & benchmark proof", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "Agent / eval harness", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ] ] }, "rank": 758, "is_new": false, "commits_delta": 0, "rank_delta": -273, "commits_delta_last_run": 0 }, { "full_name": "falcon123212/roomprint", "html_url": "https://github.com/falcon123212/roomprint", "track": "Build for Your World", "domain": "Multimodal Vision & Video (SAM / Vision)", "summary": "Reconstructs rooms in 3D from user video with depth engine", "readme_summary": "Processes user video into depth maps and 3D reconstruction with native spatial engine DLL. Includes live spatial server, offline master reconstruction, and benchmarks for depth quality, stability and end-to-end.", "tech_highlights": [ "Depth Estimation", "3D Reconstruction", "Python + Native DLL" ], "created_at": "2026-10-27T21:57:59Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 12, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": false, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.5, "score_meta_tooling": 0.5, "score_tech_depth": 0.8, "score_demo": 0.4, "score_total": 3.2, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ] ], "meta": [ [ "Base", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "5+ window commits (12)", "+0.2" ], [ "Automated test suite", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ] ] }, "rank": 759, "is_new": false, "commits_delta": 11, "rank_delta": -271, "commits_delta_last_run": 0 }, { "full_name": "NOOROWAISSI/meta-ai-hackathon-2026", "html_url": "https://github.com/NOOROWAISSI/meta-ai-hackathon-2026", "track": "Build for Your World", "domain": "Education & Knowledge Systems", "summary": "Hackathon discovery platform with prep plans for student teams", "readme_summary": "Platform helps Palestinian students find hackathons, check eligibility and generate prep plans. Stack is React TypeScript frontend, ASP.NET Core API, MySQL and Meta Models. Current frontend uses demo data, backend not connected.", "tech_highlights": [ "React + TypeScript", "ASP.NET Core API", "Meta Models" ], "created_at": "2026-10-27T06:39:08Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 7, "commits_before_window": 0, "prs_total": 24, "prs_merged": 14, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": true, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 2, "score_impact": 1.3, "score_meta_tooling": 0.5, "score_tech_depth": 1.0, "score_demo": 0.4, "score_total": 3.2, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "5+ window commits (7)", "+0.2" ], [ "Modular src/ architecture", "+0.3" ], [ "PR review workflow (14 PRs)", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ] ] }, "rank": 760, "is_new": false, "commits_delta": 0, "rank_delta": -335, "commits_delta_last_run": 0 }, { "full_name": "EvarestTechnologies/lipwad", "html_url": "https://github.com/EvarestTechnologies/lipwad", "track": "Build for Your World", "domain": "Healthcare, Civic Tech & Sustainability", "summary": "Turns paper records and Swahili voice notes into verified SHA claims.", "readme_summary": "Multimodal agent that converts photos of paper records and Swahili voice notes into SHA claims. Docs and design focused repo with cited-field verification. Built on Meta Muse models for extraction and validation.", "tech_highlights": [ "Muse Models", "Swahili Voice AI", "SHA Claims" ], "created_at": "2026-10-27T05:33:34Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 5, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": false, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.4, "score_meta_tooling": 0.5, "score_tech_depth": 0.5, "score_demo": 0.8, "score_total": 3.2, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "High-impact domain", "+0.4" ] ], "meta": [ [ "Base", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "5+ window commits (5)", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ] ] }, "rank": 761, "is_new": false, "commits_delta": 0, "rank_delta": -307, "commits_delta_last_run": 0 }, { "full_name": "Valentinpico/canline-qc-agent", "html_url": "https://github.com/Valentinpico/canline-qc-agent", "track": "Build for Your World", "domain": "Robotics, IoT & Manufacturing", "summary": "Vision QC agent for canning lines with SPC and batch-hold decisions.", "readme_summary": "Agentic quality control for food canning lines using vision inspection and operator voice notes with SPC logic. README cites SAM 3.1 and Muse Spark vision. Architecture details limited to single README.", "tech_highlights": [ "SAM 3.1 Vision", "Muse Spark", "SPC + Voice Notes" ], "created_at": "2026-10-26T17:28:45Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 1, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": false, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.4, "score_meta_tooling": 1.1, "score_tech_depth": 0.3, "score_demo": 0.4, "score_total": 3.2, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "High-impact domain", "+0.4" ] ], "meta": [ [ "Base", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ] ] }, "rank": 762, "is_new": false, "commits_delta": 0, "rank_delta": -345, "commits_delta_last_run": 0 }, { "full_name": "Jemeelah1/explain-naija", "html_url": "https://github.com/Jemeelah1/explain-naija", "track": "Build for Your World", "domain": "Education & Knowledge Systems", "summary": "Next.js app placeholder, likely Nigerian-focused explainer tool.", "readme_summary": "Repository is a Next.js create-next-app scaffold with standard src/public/config files. No functional README or Meta AI / Muse usage documented. Name suggests an explainer app, details to be implemented.", "tech_highlights": [ "Next.js + TypeScript", "Early Scaffold", "Explainer Concept" ], "created_at": "2026-10-28T23:24:01Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 1, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": true, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.3, "score_meta_tooling": 0.5, "score_tech_depth": 0.6, "score_demo": 0.8, "score_total": 3.2, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ] ] }, "rank": 763, "is_new": false, "commits_delta": 0, "rank_delta": -316, "commits_delta_last_run": 0 }, { "full_name": "HenryTech12/imagine-os-v1-META_AI_DEVELOPER_HACKATHON_2026", "html_url": "https://github.com/HenryTech12/imagine-os-v1-META_AI_DEVELOPER_HACKATHON_2026", "track": "Track 1: Build for Your World", "domain": "Consumer & Productivity", "summary": "", "readme_summary": "", "tech_highlights": [], "created_at": "2026-10-29T08:29:25Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 1, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.4, "score_meta_tooling": 0.5, "score_tech_depth": 0.9, "score_demo": 0.4, "score_total": 3.2, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "General domain", "+0.2" ], [ "Multi-module scope (>10 files)", "+0.2" ] ], "meta": [ [ "Base", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ] ] }, "rank": 764, "is_new": true, "commits_delta": 1, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "degordonstech/mypaddy", "html_url": "https://github.com/degordonstech/mypaddy", "track": "Build for Your World", "domain": "Autonomous Agents & Workflow Automation", "summary": "Telegram assistant that remembers facts, sends reminders and checks fake products", "readme_summary": "MyPaddy is a Telegram assistant for memory, reminders, fake-product checks and small tasks via text, voice, photo, video and PDF. Node/TypeScript stack with human approval gate. Uses Muse Spark, SAM 3.1, Muse Image and Muse Voice Transcribe.", "tech_highlights": [ "Muse Spark", "SAM 3.1 Vision", "Muse Voice Transcribe" ], "created_at": "2026-10-27T07:00:56Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 53, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": true, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": true, "video_urls": [ "https://youtu.be/MoJJxuz209I" ], "has_live_deploy": true, "live_urls": [ "https://degordonstech.github.io/mypaddy/" ], "anti_project_flag": "Banned Medical / Health Advisor", "is_disqualified": true, "stars": 0, "score_impact": 1.9, "score_meta_tooling": 1.8, "score_tech_depth": 1.7, "score_demo": 2.5, "score_total": 3.16, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "High-impact domain", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (53)", "+0.6" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Automated CI workflow", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Video walkthrough", "+1.1" ], [ "Reproducible setup guide", "+0.4" ], [ "Live web deployment", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 765, "is_new": true, "commits_delta": 53, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "prohle/schedulegod-ai", "html_url": "https://github.com/prohle/schedulegod-ai", "track": "Build for Your World", "domain": "Autonomous Agents & Workflow Automation", "summary": "Agentic university timetabler where AI proposes constraints and solvers verify them.", "readme_summary": "Same codebase as ScheduleSolve AI for verified academic timetabling with constraint programming. Stack is Python backend, Next.js frontend, Docker, and spectral graph analysis. Uses Muse Spark and Meta models to propose and explain schedules.", "tech_highlights": [ "Muse Spark", "CP-SAT Solver", "Next.js + FastAPI" ], "created_at": "2026-10-27T12:45:48Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 105, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": true, "has_tests": true, "has_src": true, "has_ci": true, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": true, "video_urls": [ "https://github.com/prohle/schedulesolve-ai/releases/download/demo-video/final.mp4" ], "has_live_deploy": true, "live_urls": [ "https://prohle--schedulesolve-ai-ui-web.us-east.modal.run", "https://prohle--schedulesolve-ai-api.us-east.modal.run" ], "anti_project_flag": "Medical Advice / Diagnostic (Banned Anti-Project)", "is_disqualified": true, "stars": 0, "score_impact": 2.3, "score_meta_tooling": 1.3, "score_tech_depth": 1.7, "score_demo": 2.5, "score_total": 3.12, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "High-impact domain", "+0.4" ], [ "Docker packaging", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (105)", "+0.6" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Automated CI workflow", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Video walkthrough", "+1.1" ], [ "Reproducible setup guide", "+0.4" ], [ "Live web deployment", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 766, "is_new": false, "commits_delta": 91, "rank_delta": -227, "commits_delta_last_run": 6 }, { "full_name": "manueljpconde/meta-ai-developer-hackathon", "html_url": "https://github.com/manueljpconde/meta-ai-developer-hackathon", "track": "Build for Your World", "domain": "Business, Sales & Commerce", "summary": "Calculator for Portuguese agents to track net commissions", "readme_summary": "PropWare Agentimo web app with app, engine and prototype folders for MVP analysis. Helps independent real estate agents in Portugal estimate expected pay and net share. Built as Meta AI Developer Hackathon entry.", "tech_highlights": [ "Real Estate MVP", "Commission Engine", "Meta AI Hackathon" ], "created_at": "2026-10-26T17:32:35Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 28, "commits_before_window": 29, "prs_total": 29, "prs_merged": 28, "is_preexisting": true, "has_docker": false, "has_tests": false, "has_src": true, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.3, "score_meta_tooling": 0.5, "score_tech_depth": 0.9, "score_demo": 0.4, "score_total": 3.1, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (28)", "+0.4" ], [ "Modular src/ architecture", "+0.3" ], [ "PR review workflow (28 PRs)", "+0.2" ], [ "Pre-Oct 26 commits dominate (29)", "-0.3" ] ], "demo": [ [ "Base", "+0.4" ] ] }, "rank": 767, "is_new": false, "commits_delta": 17, "rank_delta": -344, "commits_delta_last_run": 0 }, { "full_name": "JAEHUN-AN/claimlens", "html_url": "https://github.com/JAEHUN-AN/claimlens", "track": "Build for Your World", "domain": "Healthcare, Civic Tech & Sustainability", "summary": "Converts foreign hospital bill photos into checked English insurance claim packs", "readme_summary": "Reads bill photos and produces checked claim with deductible, eligibility and codes in seconds. Python backend with static frontend, samples and traceable calculations. Uses Muse Spark for reading and reasoning while code counts and people decide.", "tech_highlights": [ "Muse Spark", "OCR + Rules Engine", "Python + Static UI" ], "created_at": "2026-10-26T23:49:50Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 116, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": true, "has_setup_guide": true, "has_video_demo": true, "video_urls": [ "https://youtu.be/EApPyH3sjwA" ], "has_live_deploy": true, "live_urls": [ "https://jaehun-an.github.io/claimlens/" ], "anti_project_flag": "Banned Medical / Health Advisor", "is_disqualified": true, "stars": 0, "score_impact": 2.2, "score_meta_tooling": 1.3, "score_tech_depth": 1.7, "score_demo": 2.5, "score_total": 3.08, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "High-impact domain", "+0.4" ], [ "Eval & benchmark proof", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (116)", "+0.6" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Agent / eval harness", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Video walkthrough", "+1.1" ], [ "Reproducible setup guide", "+0.4" ], [ "Live web deployment", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 768, "is_new": false, "commits_delta": 21, "rank_delta": -238, "commits_delta_last_run": 0 }, { "full_name": "genda-benjamin/verifiable-evidence-agent", "html_url": "https://github.com/genda-benjamin/verifiable-evidence-agent", "track": "Push the Frontier", "domain": "Legal & Compliance", "summary": "Answers security questionnaires only with cryptographically proven evidence", "readme_summary": "Generates customer proof packs where browser re-verifies every cited record, signature and approval. Refuses or flags tampering when evidence is missing, built on Muse Spark and Muse Spark Open. Python vea package with evals, samples and docs.", "tech_highlights": [ "Muse Spark + Open", "Signed Evidence Pack", "Python Eval Suite" ], "created_at": "2026-10-26T16:45:06Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 40, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": false, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": true, "has_eval_benchmarks": true, "has_setup_guide": false, "has_video_demo": true, "video_urls": [ "https://youtu.be/98W0r-meZxk" ], "has_live_deploy": true, "live_urls": [ "https://genda-benjamin.github.io/verifiable-evidence-agent/" ], "anti_project_flag": "Banned Basic RAG", "is_disqualified": true, "stars": 1, "score_impact": 2.5, "score_meta_tooling": 1.8, "score_tech_depth": 1.2, "score_demo": 2.1, "score_total": 3.04, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "Domain alignment", "+0.3" ], [ "Eval & benchmark proof", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "Open-weights / fine-tuning", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (40)", "+0.4" ], [ "Automated test suite", "+0.3" ], [ "Agent / eval harness", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Video walkthrough", "+1.1" ], [ "Live web deployment", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 769, "is_new": false, "commits_delta": 0, "rank_delta": -313, "commits_delta_last_run": 0 }, { "full_name": "AllMindkind-ops/hackathon-meta-2026", "html_url": "https://github.com/AllMindkind-ops/hackathon-meta-2026", "track": "Build for Your World", "domain": "General & Emerging Applications", "summary": "Simple static web page with light and dark theme assets.", "readme_summary": "Simple static web page with light and dark theme assets.", "tech_highlights": [], "created_at": "2026-10-27T12:23:26Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 77, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": false, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.2, "score_meta_tooling": 0.5, "score_tech_depth": 0.9, "score_demo": 0.4, "score_total": 3.0, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "General domain", "+0.2" ] ], "meta": [ [ "Base", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (77)", "+0.6" ] ], "demo": [ [ "Base", "+0.4" ] ] }, "rank": 770, "is_new": false, "commits_delta": 60, "rank_delta": -337, "commits_delta_last_run": 0 }, { "full_name": "dembenski/star-sprite", "html_url": "https://github.com/dembenski/star-sprite", "track": "Build for Your World", "domain": "Gaming, Entertainment & Creative Media", "summary": "Prompt-to-playable game engine that generates browser games instantly", "readme_summary": "AI game-making engine where prompt in yields playable game out in browser. Single index.html frontend architecture. Uses Muse Wonder muse-wonder-1.0 with Groq backup for generation.", "tech_highlights": [ "Muse Wonder 1.0", "Groq Backup", "HTML5 Games" ], "created_at": "2026-10-26T17:05:57Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 70, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": false, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.2, "score_meta_tooling": 0.5, "score_tech_depth": 0.9, "score_demo": 0.4, "score_total": 3.0, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "General domain", "+0.2" ] ], "meta": [ [ "Base", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (70)", "+0.6" ] ], "demo": [ [ "Base", "+0.4" ] ] }, "rank": 771, "is_new": false, "commits_delta": 30, "rank_delta": -340, "commits_delta_last_run": 0 }, { "full_name": "NoBanks/nightride", "html_url": "https://github.com/NoBanks/nightride", "track": "Build for Your World", "domain": "Voice, Speech & Audio AI", "summary": "Voice-button night dispatcher for cyclists and walkers stranded after dark", "readme_summary": "Installable phone PWA with offline support; hold one button to speak, get next spoken action with sources. Node server plus shared client with e2e tests. Built for hackathon using Meta AI for dispatch reasoning.", "tech_highlights": [ "Voice-First PWA", "Muse Spark", "Offline Installable" ], "created_at": "2026-10-28T21:03:00Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 35, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": true, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": true, "video_urls": [ "https://youtu.be/ZW6jwK26yeE" ], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Banned Medical / Health Advisor", "is_disqualified": true, "stars": 0, "score_impact": 1.8, "score_meta_tooling": 2.3, "score_tech_depth": 1.3, "score_demo": 2.1, "score_total": 3.0, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ], [ "Open-weights / fine-tuning", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (35)", "+0.4" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Video walkthrough", "+1.1" ], [ "Reproducible setup guide", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 772, "is_new": false, "commits_delta": 23, "rank_delta": -226, "commits_delta_last_run": 0 }, { "full_name": "jiyoung-ai-lab/nsp3d-hackathon", "html_url": "https://github.com/jiyoung-ai-lab/nsp3d-hackathon", "track": "Build for Your World", "domain": "Education & Knowledge Systems", "summary": "3D fruit-fly connectome flight simulator showing vision to behavior flow", "readme_summary": "Three.js visualization of Drosophila Male CNS v1.0 circuits driving virtual flight in maze environments. JavaScript + spiking neural network simulation, with analysis assisted by Meta Muse Spark.", "tech_highlights": [ "Three.js + WebGL", "Spiking Neural Net", "Muse Spark" ], "created_at": "2026-11-01T14:27:44Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 5, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": false, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 1, "score_impact": 1.3, "score_meta_tooling": 0.8, "score_tech_depth": 0.5, "score_demo": 0.4, "score_total": 3.0, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Muse Spark integration", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "5+ window commits (5)", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ] ] }, "rank": 773, "is_new": true, "commits_delta": 5, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "nudiiir/elixir-distribution", "html_url": "https://github.com/nudiiir/elixir-distribution", "track": "Build for Your World", "domain": "Business, Sales & Commerce", "summary": "Offline-first distribution ERP for orders, stock and delivery in Algeria", "readme_summary": "Offline-first management system for distributors and shops covering stock, invoicing, delivery rounds and online store. Runs on local PCs with app, server and installer folders. Hackathon adds AI features to existing product.", "tech_highlights": [ "Offline-First ERP", "Orders + Stock + CRM", "Meta AI Features" ], "created_at": "2026-10-27T14:03:39Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 3, "commits_before_window": 25, "prs_total": 0, "prs_merged": 0, "is_preexisting": true, "has_docker": false, "has_tests": false, "has_src": true, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.6, "score_meta_tooling": 0.5, "score_tech_depth": 0.3, "score_demo": 0.6, "score_total": 3.0, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Pre-Oct 26 commits dominate (25)", "-0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 774, "is_new": false, "commits_delta": 0, "rank_delta": -372, "commits_delta_last_run": 0 }, { "full_name": "gentcod/flatmate", "html_url": "https://github.com/gentcod/flatmate", "track": "Build for Your World", "domain": "General & Emerging Applications", "summary": "Rule-based flatmate matcher scoring living habits with AI explanations", "readme_summary": "Flatmate matching app with signup, profiles, and 11-question habit survey. Go backend with rule-based 0-100 scoring from weights.yaml plus optional Muse narration. AI only explains precomputed scores and works disabled.", "tech_highlights": [ "Go backend", "Rule-based matching", "Muse narration" ], "created_at": "2026-10-30T18:50:31Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 3, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": false, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.4, "score_meta_tooling": 0.5, "score_tech_depth": 0.3, "score_demo": 0.8, "score_total": 3.0, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "General domain", "+0.2" ], [ "Multi-module scope (>10 files)", "+0.2" ] ], "meta": [ [ "Base", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ] ] }, "rank": 775, "is_new": true, "commits_delta": 3, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "Emmlin-Tech/Solution", "html_url": "https://github.com/Emmlin-Tech/Solution", "track": "Build for Your World", "domain": "Education & Knowledge Systems", "summary": "Pidgin English AI support concept for 100M Nigerian speakers", "readme_summary": "Proposes an AI support model for Nigerian Pidgin English speakers. Repo contains only README with images and problem statement doc, no code or architecture. No Meta AI / Muse integration is implemented or documented.", "tech_highlights": [ "Pidgin NLP Concept", "No Codebase" ], "created_at": "2026-10-30T11:33:47Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 3, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": false, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": true, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.6, "score_meta_tooling": 0.5, "score_tech_depth": 0.5, "score_demo": 0.4, "score_total": 3.0, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Eval & benchmark proof", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "Agent / eval harness", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ] ] }, "rank": 776, "is_new": true, "commits_delta": 3, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "kin2001/shofiliate-ai", "html_url": "https://github.com/kin2001/shofiliate-ai", "track": "Build for Your World", "domain": "Business, Sales & Commerce", "summary": "Guides affiliates from product research to content drafts and Facebook posts", "readme_summary": "Planned workflow for product analysis, AI-assisted campaign drafting, review and Facebook publishing. Keeps user approval in loop while linking decisions to performance tracking. Designed around Meta AI content assistance.", "tech_highlights": [ "Campaign Generator", "Facebook Publishing", "Performance Tracking" ], "created_at": "2026-10-26T08:32:19Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 2, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": false, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": true, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.6, "score_meta_tooling": 0.5, "score_tech_depth": 0.5, "score_demo": 0.4, "score_total": 3.0, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Eval & benchmark proof", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "Agent / eval harness", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ] ] }, "rank": 777, "is_new": false, "commits_delta": 0, "rank_delta": -310, "commits_delta_last_run": 0 }, { "full_name": "valon85/codren-one-sentence-app", "html_url": "https://github.com/valon85/codren-one-sentence-app", "track": "Build for Your World", "domain": "General & Emerging Applications", "summary": "Turns one sentence into working apps using Meta-only model router", "readme_summary": "CODREN prompt-to-plan-to-app generator switched to run 100% on Meta models. Powers live products Briovix and Spicey with chat and image generation. Verified via call logs showing muse-spark-1.3 serving.", "tech_highlights": [ "Muse Spark 1.3", "Muse Image", "Prompt-to-App" ], "created_at": "2026-10-27T21:18:36Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 2, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": false, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.2, "score_meta_tooling": 1.1, "score_tech_depth": 0.3, "score_demo": 0.4, "score_total": 3.0, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "General domain", "+0.2" ] ], "meta": [ [ "Base", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ] ] }, "rank": 778, "is_new": false, "commits_delta": 0, "rank_delta": -335, "commits_delta_last_run": 0 }, { "full_name": "blackjacksu/agent-bureau", "html_url": "https://github.com/blackjacksu/agent-bureau", "track": "Push the Frontier", "domain": "Autonomous Agents & Workflow Automation", "summary": "Initialized agent-focused repo with no implemented features yet.", "readme_summary": "Repo agent-bureau contains only an initialization placeholder stating more coming soon. No code, stack, architecture, or Meta AI / Muse integration is described in README or file tree.", "tech_highlights": [], "created_at": "2026-10-27T01:52:11Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 2, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": false, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.8, "score_meta_tooling": 0.5, "score_tech_depth": 0.3, "score_demo": 0.4, "score_total": 3.0, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "High-impact domain", "+0.4" ] ], "meta": [ [ "Base", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ] ] }, "rank": 779, "is_new": true, "commits_delta": 2, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "B-A-M-N/X-factor-Meta-Hackathon-2026", "html_url": "https://github.com/B-A-M-N/X-factor-Meta-Hackathon-2026", "track": "Push the Frontier", "domain": "Developer Tooling, Infra & Security", "summary": "Index of four modular dev tools for gateways, tunnels and agent control", "readme_summary": "Lightweight index repo, not a monorepo, linking Locus gateway, Ocliv tunnel, Metis terminal, and Jeverb verification. Each module has independent codebase and release process. No integration code.", "tech_highlights": [ "AI Gateway", "Agent Verification", "Secure Tunnels" ], "created_at": "2026-10-31T15:26:19Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 2, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": false, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.8, "score_meta_tooling": 0.5, "score_tech_depth": 0.3, "score_demo": 0.4, "score_total": 3.0, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "High-impact domain", "+0.4" ] ], "meta": [ [ "Base", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ] ] }, "rank": 780, "is_new": true, "commits_delta": 2, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "corefex/testigo", "html_url": "https://github.com/corefex/testigo", "track": "Push the Frontier", "domain": "Developer Tooling, Infra & Security", "summary": "Verifies agent payment actions match intent before execution.", "readme_summary": "TESTIGO+ prototype checks proposed payment action against authorized intent and approval. Blocks execution or requests re-approval on material mismatch. README-only repo, no stack or Muse model details disclosed.", "tech_highlights": [ "Agent Guardrail", "Payment Verification", "Policy Enforcement" ], "created_at": "2026-10-30T03:19:13Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 1, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": false, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 1, "score_impact": 1.8, "score_meta_tooling": 0.5, "score_tech_depth": 0.3, "score_demo": 0.4, "score_total": 3.0, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "High-impact domain", "+0.4" ] ], "meta": [ [ "Base", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ] ] }, "rank": 781, "is_new": true, "commits_delta": 1, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "parthivpatel-patel/meta-ai-hackathon-2026", "html_url": "https://github.com/parthivpatel-patel/meta-ai-hackathon-2026", "track": "Push the Frontier", "domain": "Autonomous Agents & Workflow Automation", "summary": "Framework for verifiable multimodal AI agents", "readme_summary": "Independent hackathon project exploring verifiable multimodal agents. README is minimal with no architecture detailed. Focus is on agent verification methods using Meta AI models.", "tech_highlights": [ "Multimodal agents", "Verification framework", "Meta AI" ], "created_at": "2026-10-26T15:59:02Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 1, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": false, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.8, "score_meta_tooling": 0.5, "score_tech_depth": 0.3, "score_demo": 0.4, "score_total": 3.0, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "High-impact domain", "+0.4" ] ], "meta": [ [ "Base", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ] ] }, "rank": 782, "is_new": false, "commits_delta": 0, "rank_delta": -307, "commits_delta_last_run": 0 }, { "full_name": "SpiritX12/AwasScanAgent", "html_url": "https://github.com/SpiritX12/AwasScanAgent", "track": "Push the Frontier", "domain": "Developer Tooling, Infra & Security", "summary": "Telegram bot checking scams in messages, QR codes and voice notes", "readme_summary": "Telegram bot investigating suspicious Malaysian messages, screenshots, QRs and voice notes. Uses QR decoding, link checks, transcription tools with Muse models for verdicts. Built on Telegram bot stack.", "tech_highlights": [ "Muse models", "Telegram bot", "QR + transcription" ], "created_at": "2026-10-28T07:41:55Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 1, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": false, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.8, "score_meta_tooling": 0.5, "score_tech_depth": 0.3, "score_demo": 0.4, "score_total": 3.0, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "High-impact domain", "+0.4" ] ], "meta": [ [ "Base", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ] ] }, "rank": 783, "is_new": false, "commits_delta": 0, "rank_delta": -304, "commits_delta_last_run": 0 }, { "full_name": "urieltisera/b1-gate2-demo", "html_url": "https://github.com/urieltisera/b1-gate2-demo", "track": "Push the Frontier", "domain": "Developer Tooling, Infra & Security", "summary": "Disposable demo for controlled-effect B1 evaluation", "readme_summary": "B1 controlled-effect disposable repository for the Meta hackathon. Minimal README with no stack or model usage described. Appears to be an infra evaluation demo.", "tech_highlights": [ "Demo repo", "Controlled-effect", "Meta AI" ], "created_at": "2026-10-27T19:43:11Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 1, "commits_before_window": 0, "prs_total": 1, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": false, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.8, "score_meta_tooling": 0.5, "score_tech_depth": 0.3, "score_demo": 0.4, "score_total": 3.0, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "High-impact domain", "+0.4" ] ], "meta": [ [ "Base", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ] ] }, "rank": 784, "is_new": false, "commits_delta": 0, "rank_delta": -302, "commits_delta_last_run": 0 }, { "full_name": "Abm32/pathya", "html_url": "https://github.com/Abm32/pathya", "track": "Build for Your World", "domain": "Healthcare, Civic Tech & Sustainability", "summary": "Converts Indian pharmacogenomic PDFs and photos into de-identified research data", "readme_summary": "Reads lab PDFs, WhatsApp photos and dictation into verified de-identified records and cohort frequencies. Uses Meta Muse models for extraction, aggregation pipeline, research-only tool.", "tech_highlights": [ "Muse Models", "PDF + OCR Pipeline", "Docker + Cohort DB" ], "created_at": "2026-10-26T18:27:33Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 61, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": true, "has_tests": false, "has_src": true, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": true, "video_urls": [ "https://youtu.be/21679gHAEqc" ], "has_live_deploy": true, "live_urls": [ "https://pathya.anukritiai.com" ], "anti_project_flag": "Banned Medical / Health Advisor", "is_disqualified": true, "stars": 0, "score_impact": 2.3, "score_meta_tooling": 1.3, "score_tech_depth": 1.2, "score_demo": 2.5, "score_total": 2.92, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "High-impact domain", "+0.4" ], [ "Docker packaging", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (61)", "+0.6" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Video walkthrough", "+1.1" ], [ "Reproducible setup guide", "+0.4" ], [ "Live web deployment", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 785, "is_new": true, "commits_delta": 61, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "henryokeke/-AttendAI-2.0-Meta-Hackathon", "html_url": "https://github.com/henryokeke/-AttendAI-2.0-Meta-Hackathon", "track": "Build for Your World", "domain": "Education & Knowledge Systems", "summary": "Anti-proxy school attendance with liveness check, voice print and analytics.", "readme_summary": "FastAPI attendance system for rural schools with liveness anti-spoofing and location check. Supports voice marking in Igbo, Pidgin, English offline. Uses Llama 3 via Muse for at-risk insights and analytics.", "tech_highlights": [ "Llama 3", "Liveness Detect", "FastAPI" ], "created_at": "2026-10-26T16:57:46Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 4, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": false, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.3, "score_meta_tooling": 0.5, "score_tech_depth": 0.3, "score_demo": 0.8, "score_total": 2.9, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ] ] }, "rank": 786, "is_new": false, "commits_delta": 0, "rank_delta": -258, "commits_delta_last_run": 0 }, { "full_name": "0FFSTYLE/Meta-Global-developer-AI-hackathon-2026", "html_url": "https://github.com/0FFSTYLE/Meta-Global-developer-AI-hackathon-2026", "track": "Build for Your World", "domain": "General & Emerging Applications", "summary": "", "readme_summary": "", "tech_highlights": [], "created_at": "2026-10-27T15:30:51Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 3, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": false, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.4, "score_meta_tooling": 0.5, "score_tech_depth": 0.6, "score_demo": 0.4, "score_total": 2.9, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "General domain", "+0.2" ], [ "Multi-module scope (>10 files)", "+0.2" ] ], "meta": [ [ "Base", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "Automated test suite", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ] ] }, "rank": 787, "is_new": false, "commits_delta": 0, "rank_delta": -379, "commits_delta_last_run": 0 }, { "full_name": "albertojbravo-art/shift-copilot", "html_url": "https://github.com/albertojbravo-art/shift-copilot", "track": "Build for Your World", "domain": "Robotics, IoT & Manufacturing", "summary": "Forecasts warehouse on-time shipping and recommends staffing moves for leads", "readme_summary": "Deterministic Python simulation engine computes OTS forecasts and scan-gap stoppage detection. Recommends cross-area staffing moves and drafts extra-staff postings. Built with Muse during hackathon using synthetic demo data.", "tech_highlights": [ "Muse Copilot", "Python Simulation", "OTS Forecasting" ], "created_at": "2026-10-27T23:42:15Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 2, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": false, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.4, "score_meta_tooling": 0.5, "score_tech_depth": 0.6, "score_demo": 0.4, "score_total": 2.9, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "High-impact domain", "+0.4" ] ], "meta": [ [ "Base", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "Automated test suite", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ] ] }, "rank": 788, "is_new": false, "commits_delta": 0, "rank_delta": -346, "commits_delta_last_run": 0 }, { "full_name": "leo-leo-691/wildwitness", "html_url": "https://github.com/leo-leo-691/wildwitness", "track": "Build for Your World", "domain": "Healthcare, Civic Tech & Sustainability", "summary": "Turns camera-trap images and audio into wildlife counts and alerts", "readme_summary": "Wildlife monitoring app converting camera-trap images and audio to population counts. Generates poaching alerts from detections. Built for conservation using Meta AI vision and audio models.", "tech_highlights": [ "Vision + Audio AI", "Wildlife detection", "Poaching alerts" ], "created_at": "2026-10-27T14:53:27Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 2, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": false, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.4, "score_meta_tooling": 0.5, "score_tech_depth": 0.6, "score_demo": 0.4, "score_total": 2.9, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "High-impact domain", "+0.4" ] ], "meta": [ [ "Base", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "Automated test suite", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ] ] }, "rank": 789, "is_new": false, "commits_delta": 1, "rank_delta": -309, "commits_delta_last_run": 0 }, { "full_name": "BO01OK/agentic-observability-llama", "html_url": "https://github.com/BO01OK/agentic-observability-llama", "track": "Push the Frontier", "domain": "Developer Tooling, Infra & Security", "summary": "Observability and self-healing guardrails for production AI agents", "readme_summary": "Provides production-grade observability and self-healing for autonomous agents to reduce failure cost and MTTR. Includes architecture PDF plus README with guardrail cost comparison. Built on Llama-family models for agent monitoring.", "tech_highlights": [ "Llama Guardrails", "Agent Observability", "Self-Healing Infra" ], "created_at": "2026-10-25T12:14:04Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 1, "commits_before_window": 2, "prs_total": 0, "prs_merged": 0, "is_preexisting": true, "has_docker": false, "has_tests": false, "has_src": false, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 1, "score_impact": 1.8, "score_meta_tooling": 0.5, "score_tech_depth": 0.2, "score_demo": 0.4, "score_total": 2.9, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "High-impact domain", "+0.4" ] ], "meta": [ [ "Base", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "Pre-existing repo (<=2 commits)", "-0.5" ] ], "demo": [ [ "Base", "+0.4" ] ] }, "rank": 790, "is_new": false, "commits_delta": 0, "rank_delta": -291, "commits_delta_last_run": 0 }, { "full_name": "Quentintnrl/mealkinator", "html_url": "https://github.com/Quentintnrl/mealkinator", "track": "Build for Your World", "domain": "General & Emerging Applications", "summary": "Weekly meal-planner demo used as test target for codegen workflow.", "readme_summary": "Vite + TypeScript demo app serving as decor for Ripple_handoff, which builds features from Figma and verifies results. Contains brand/docs and assets only, no product code yet. No direct Meta AI / Muse usage in this repo.", "tech_highlights": [ "Vite + TypeScript", "Figma-to-Code Target", "Demo Harness" ], "created_at": "2026-10-26T20:20:53Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 1, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": true, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.4, "score_meta_tooling": 0.5, "score_tech_depth": 0.6, "score_demo": 0.4, "score_total": 2.9, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "General domain", "+0.2" ], [ "Multi-module scope (>10 files)", "+0.2" ] ], "meta": [ [ "Base", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ] ] }, "rank": 791, "is_new": false, "commits_delta": 0, "rank_delta": -372, "commits_delta_last_run": 0 }, { "full_name": "Eswereddy/krishi-mitra-agent", "html_url": "https://github.com/Eswereddy/krishi-mitra-agent", "track": "Build for Your World", "domain": "Voice, Speech & Audio AI", "summary": "Telugu/Hindi/English voice farming helper for diagnosis, prices, schemes", "readme_summary": "Voice-first agent accepts speech, text or crop photo in Telugu, Hindi, English with auto-detect and spoken answers. Single agent does vision diagnosis, weather timing, mandi prices and scheme eligibility. Backend + frontend in Docker, built on Meta Muse models.", "tech_highlights": [ "Muse Models", "Telugu Voice + Vision", "Docker Backend" ], "created_at": "2026-10-28T00:42:33Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 113, "commits_before_window": 0, "prs_total": 29, "prs_merged": 29, "is_preexisting": false, "has_docker": true, "has_tests": false, "has_src": true, "has_ci": true, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": true, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Medical Advice / Diagnostic (Banned Anti-Project)", "is_disqualified": true, "stars": 0, "score_impact": 2.2, "score_meta_tooling": 2.3, "score_tech_depth": 1.6, "score_demo": 1.0, "score_total": 2.84, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Docker packaging", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ], [ "Open-weights / fine-tuning", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (113)", "+0.6" ], [ "Modular src/ architecture", "+0.3" ], [ "Automated CI workflow", "+0.2" ], [ "PR review workflow (29 PRs)", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 792, "is_new": false, "commits_delta": 64, "rank_delta": -256, "commits_delta_last_run": 0 }, { "full_name": "Cengkudu800mdpl/catat-panen-ai-2026", "html_url": "https://github.com/Cengkudu800mdpl/catat-panen-ai-2026", "track": "Build for Your World", "domain": "Healthcare, Civic Tech & Sustainability", "summary": "Log farm harvests in Banyumas by voice in Indonesian or Javanese plus crop photos.", "readme_summary": "Simple app for Banyumas farmers to record harvests via voice and auto-detect crop photos with daily recaps. Built with Next.js and WhatsApp API using Meta Llama 4 for Indonesian and Banyumasan language input.", "tech_highlights": [ "Meta Llama 4", "WhatsApp API", "Next.js" ], "created_at": "2026-10-27T12:54:36Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 10, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": false, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.4, "score_meta_tooling": 0.5, "score_tech_depth": 0.5, "score_demo": 0.4, "score_total": 2.8, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "High-impact domain", "+0.4" ] ], "meta": [ [ "Base", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "5+ window commits (10)", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ] ] }, "rank": 793, "is_new": false, "commits_delta": 3, "rank_delta": -341, "commits_delta_last_run": 0 }, { "full_name": "Hilta-dev/nawaflow", "html_url": "https://github.com/Hilta-dev/nawaflow", "track": "Build for Your World", "domain": "Voice, Speech & Audio AI", "summary": "Voice-first assistant helping small traders in Namibia manage business by speech.", "readme_summary": "Voice-first trading assistant for low-literacy small traders. Client-server app with Supabase backend. Uses Meta AI voice models for speech interaction in local languages.", "tech_highlights": [ "Voice AI", "Supabase", "Client + Server" ], "created_at": "2026-10-28T11:15:16Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 4, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": true, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.3, "score_meta_tooling": 0.5, "score_tech_depth": 0.6, "score_demo": 0.4, "score_total": 2.8, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ] ] }, "rank": 794, "is_new": false, "commits_delta": 0, "rank_delta": -356, "commits_delta_last_run": 0 }, { "full_name": "microwaves22/HobbyMaxer", "html_url": "https://github.com/microwaves22/HobbyMaxer", "track": "Build for Your World", "domain": "General & Emerging Applications", "summary": "Early hobby-themed hackathon repo with minimal public details yet.", "readme_summary": "Repository titled EMANO for Meta Hackathon 2026 contains only README and AGENTS.md with no functional description. No technical stack, architecture, or Meta AI / Muse usage is documented.", "tech_highlights": [], "created_at": "2026-10-26T22:03:24Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 4, "commits_before_window": 0, "prs_total": 1, "prs_merged": 1, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": false, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.2, "score_meta_tooling": 0.5, "score_tech_depth": 0.3, "score_demo": 0.8, "score_total": 2.8, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "General domain", "+0.2" ] ], "meta": [ [ "Base", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ] ] }, "rank": 795, "is_new": false, "commits_delta": 3, "rank_delta": -302, "commits_delta_last_run": 2 }, { "full_name": "lefrogfw2/outthecutAI", "html_url": "https://github.com/lefrogfw2/outthecutAI", "track": "Build for Your World", "domain": "General & Emerging Applications", "summary": "Repository with minimal README, project details not yet documented.", "readme_summary": "Repository contains only a README header with no documented functionality or stack. No architecture or Meta AI / Muse integration is described. Treated as an early-stage placeholder pending implementation.", "tech_highlights": [ "README Only", "Undisclosed Stack" ], "created_at": "2026-10-30T14:09:48Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 1, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": false, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": true, "live_urls": [ "https://outthecutai-423eb5.netlify.app" ], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.2, "score_meta_tooling": 0.5, "score_tech_depth": 0.3, "score_demo": 0.8, "score_total": 2.8, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "General domain", "+0.2" ] ], "meta": [ [ "Base", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Live web deployment", "+0.4" ] ] }, "rank": 796, "is_new": true, "commits_delta": 1, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "bawanallahbilyaminu/kasafi-agent", "html_url": "https://github.com/bawanallahbilyaminu/kasafi-agent", "track": "Build for Your World", "domain": "Healthcare, Civic Tech & Sustainability", "summary": "Hausa voice-first WhatsApp agent answering from cited public budgets and policies", "readme_summary": "WhatsApp agent answers Hausa/English voice or text from budgets, policies, weather and health registry. It cites pages/tables and verifies figures in code, fetching and indexing missing documents. Uses Muse models for Hausa understanding, retrieval and grounded answers.", "tech_highlights": [ "Muse Spark", "WhatsApp Voice Agent", "RAG + Citations" ], "created_at": "2026-10-26T18:15:04Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 432, "commits_before_window": 0, "prs_total": 2, "prs_merged": 0, "is_preexisting": false, "has_docker": true, "has_tests": true, "has_src": true, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": true, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Banned Medical / Health Advisor", "is_disqualified": true, "stars": 0, "score_impact": 2.6, "score_meta_tooling": 1.6, "score_tech_depth": 1.7, "score_demo": 1.0, "score_total": 2.76, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "High-impact domain", "+0.4" ], [ "Eval & benchmark proof", "+0.3" ], [ "Docker packaging", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (432)", "+0.6" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Agent / eval harness", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 797, "is_new": false, "commits_delta": 315, "rank_delta": -717, "commits_delta_last_run": 6 }, { "full_name": "DiegoLLBB/kernel-credit-lab", "html_url": "https://github.com/DiegoLLBB/kernel-credit-lab", "track": "Build for Your World", "domain": "Finance, Crypto & Web3", "summary": "Verifiable agentic analyst for USD investment-grade bonds", "readme_summary": "Research workbench turning SEC filings and prospectuses into cited knowledge base. Plan-gather-compute-verify-critique loop with Postgres as record and deterministic tools. Uses Muse Spark via Meta Model API for extraction and synthesis.", "tech_highlights": [ "Muse Spark", "Postgres + Tools", "Firebase + Docker" ], "created_at": "2026-10-27T12:03:16Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 64, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": true, "has_tests": false, "has_src": true, "has_ci": true, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": true, "has_eval_benchmarks": true, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Banned Basic RAG", "is_disqualified": true, "stars": 0, "score_impact": 2.2, "score_meta_tooling": 2.3, "score_tech_depth": 1.6, "score_demo": 0.8, "score_total": 2.76, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Eval & benchmark proof", "+0.3" ], [ "Docker packaging", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ], [ "Open-weights / fine-tuning", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (64)", "+0.6" ], [ "Modular src/ architecture", "+0.3" ], [ "Agent / eval harness", "+0.2" ], [ "Automated CI workflow", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ] ] }, "rank": 798, "is_new": false, "commits_delta": 39, "rank_delta": -264, "commits_delta_last_run": 1 }, { "full_name": "EmirCobanOfficial/courtsense", "html_url": "https://github.com/EmirCobanOfficial/courtsense", "track": "Build for Your World", "domain": "Multimodal Vision & Video (SAM / Vision)", "summary": "Tracks tennis players from coaching video to produce movement analytics", "readme_summary": "Analyzes a coach training video to track both players and extract movement data. Built with Next.js/TypeScript frontend using Meta Model API: SAM 3.1 for detection/tracking and Muse Spark 1.3 for reasoning.", "tech_highlights": [ "SAM 3.1 Vision", "Muse Spark 1.3", "Next.js + TypeScript" ], "created_at": "2026-10-28T11:21:38Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 27, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": true, "has_ci": true, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": false, "has_video_demo": true, "video_urls": [ "https://youtu.be/aLUSjad3vto", "https://youtu.be/C0gcC3CdusI" ], "has_live_deploy": true, "live_urls": [ "https://emircobanofficial.github.io/courtsense-site/" ], "anti_project_flag": "Banned Sports Coach/Analyzer", "is_disqualified": true, "stars": 0, "score_impact": 1.8, "score_meta_tooling": 1.8, "score_tech_depth": 1.2, "score_demo": 2.1, "score_total": 2.76, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (27)", "+0.4" ], [ "Modular src/ architecture", "+0.3" ], [ "Automated CI workflow", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Video walkthrough", "+1.1" ], [ "Live web deployment", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 799, "is_new": false, "commits_delta": 20, "rank_delta": -344, "commits_delta_last_run": 0 }, { "full_name": "gino6178/serve-meta-hackathon", "html_url": "https://github.com/gino6178/serve-meta-hackathon", "track": "Build for Your World", "domain": "Gaming, Entertainment & Creative Media", "summary": "Sports social platform where AI agents negotiate real-world play plans", "readme_summary": "Lets personal AI agents negotiate sports plans where each person says one yes. Includes live web app, agent layer, distillation and ops docs. Built on Meta open models with llms.txt agent interface during Oct 27-Nov 4 hackathon.", "tech_highlights": [ "Meta Open Models", "AI Negotiating Agents", "Web Platform + llms.txt" ], "created_at": "2026-10-28T16:10:56Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 1192, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": false, "has_ci": true, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": true, "has_eval_benchmarks": false, "has_setup_guide": false, "has_video_demo": true, "video_urls": [ "https://youtu.be/OXlW1dznFo4" ], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Banned Sports Coach/Analyzer", "is_disqualified": true, "stars": 0, "score_impact": 1.7, "score_meta_tooling": 2.3, "score_tech_depth": 1.1, "score_demo": 1.7, "score_total": 2.72, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "General domain", "+0.2" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ], [ "Open-weights / fine-tuning", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (1192)", "+0.6" ], [ "Automated CI workflow", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Video walkthrough", "+1.1" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 800, "is_new": false, "commits_delta": 267, "rank_delta": -304, "commits_delta_last_run": 0 }, { "full_name": "swapnilchaudhari007/pinchplan", "html_url": "https://github.com/swapnilchaudhari007/pinchplan", "track": "Build for Your World", "domain": "General & Emerging Applications", "summary": "Hands-first WebXR focus desk and task board for Meta Quest", "readme_summary": "Seated mixed-reality task board and focus timer built with WebXR and Three.js for Meta Quest Browser. Uses pinch and pinch-drag hand tracking without controllers. No Meta AI model integration, VR Start entry.", "tech_highlights": [ "WebXR + Three.js", "Meta Quest Hand Tracking", "Static Web Demo" ], "created_at": "2026-09-30T05:34:08Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 3, "commits_before_window": 10, "prs_total": 0, "prs_merged": 0, "is_preexisting": true, "has_docker": false, "has_tests": false, "has_src": false, "has_ci": true, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": true, "live_urls": [ "https://swapnilchaudhari007.github.io/pinchplan/" ], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.2, "score_meta_tooling": 0.5, "score_tech_depth": 0.2, "score_demo": 0.8, "score_total": 2.7, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "General domain", "+0.2" ] ], "meta": [ [ "Base", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "Automated CI workflow", "+0.2" ], [ "Pre-Oct 26 commits dominate (10)", "-0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Live web deployment", "+0.4" ] ] }, "rank": 801, "is_new": true, "commits_delta": 3, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "obstinatedev/Tryform", "html_url": "https://github.com/obstinatedev/Tryform", "track": "Build for Your World", "domain": "General & Emerging Applications", "summary": "Unity-based Tryform prototype with no documented functionality yet", "readme_summary": "Unity project with Assets, Packages, and ProjectSettings only and no README. Appears to be early-stage 3D or AR prototype for Meta hackathon. No Meta model integration visible in file tree.", "tech_highlights": [ "Unity 3D", "C# Prototype", "AR/VR Candidate" ], "created_at": "2026-10-26T22:57:19Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 1, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": true, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.2, "score_meta_tooling": 0.5, "score_tech_depth": 0.6, "score_demo": 0.4, "score_total": 2.7, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "General domain", "+0.2" ] ], "meta": [ [ "Base", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ] ] }, "rank": 802, "is_new": false, "commits_delta": 0, "rank_delta": -316, "commits_delta_last_run": 0 }, { "full_name": "Hipocratesalud/follow-up-engine", "html_url": "https://github.com/Hipocratesalud/follow-up-engine", "track": "Build for Your World", "domain": "Healthcare, Civic Tech & Sustainability", "summary": "FHIR-based engine that finds orders patients never completed and drives follow-up", "readme_summary": "Reads HL7 FHIR R4 orders, results and notes to create dated expectations for follow-up. A WhatsApp agent works orders with patients until a deterministic engine marks them done. Built on Meta Muse Spark without autonomous medical advice.", "tech_highlights": [ "Muse Spark", "HL7 FHIR R4", "WhatsApp Agent" ], "created_at": "2026-10-27T01:53:18Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 389, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": true, "has_tests": true, "has_src": true, "has_ci": true, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": true, "live_urls": [ "https://follow-up-engine-demo-production.up.railway.app" ], "anti_project_flag": "Banned Medical / Health Advisor", "is_disqualified": true, "stars": 0, "score_impact": 2.3, "score_meta_tooling": 1.3, "score_tech_depth": 1.7, "score_demo": 1.4, "score_total": 2.68, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "High-impact domain", "+0.4" ], [ "Docker packaging", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (389)", "+0.6" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Automated CI workflow", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Live web deployment", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 803, "is_new": true, "commits_delta": 389, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "mannasync/docarion-meta-multimodal", "html_url": "https://github.com/mannasync/docarion-meta-multimodal", "track": "Build for Your World", "domain": "Healthcare, Civic Tech & Sustainability", "summary": "Verifies drug authenticity and guides antibiotic use with clinical vision and Pidgin copilot.", "readme_summary": "NAFDAC/PCN counterfeit checker and antibiotic gatekeeper with bilingual Pidgin copilot. Architecture spans backend, frontend and mobile with clinical vision workflow. Uses SAM 3.1 for package inspection and Muse Spark models for guidance.", "tech_highlights": [ "SAM 3.1 Vision", "Muse Spark 1.x", "Backend + Mobile" ], "created_at": "2026-10-27T16:43:41Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 3, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": true, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": true, "has_eval_benchmarks": false, "has_setup_guide": false, "has_video_demo": true, "video_urls": [ "https://youtube.com/watch?v=YOUR_VIDEO_ID" ], "has_live_deploy": true, "live_urls": [ "https://docarion.com" ], "anti_project_flag": "Banned Medical / Health Advisor", "is_disqualified": true, "stars": 0, "score_impact": 1.7, "score_meta_tooling": 2.3, "score_tech_depth": 0.6, "score_demo": 2.1, "score_total": 2.68, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "High-impact domain", "+0.4" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ], [ "Open-weights / fine-tuning", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Video walkthrough", "+1.1" ], [ "Live web deployment", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 804, "is_new": false, "commits_delta": 2, "rank_delta": -309, "commits_delta_last_run": 0 }, { "full_name": "Tways-study/Basa", "html_url": "https://github.com/Tways-study/Basa", "track": "Build for Your World", "domain": "Healthcare, Civic Tech & Sustainability", "summary": "Photographs paper clinic charts into human-verified digital records", "readme_summary": "Basa captures offline chart photos, segments regions and runs two independent model readings with reconciliation UI. Stack is Next.js, Supabase with eval harness. Uses Muse Spark for extraction and SAM 3.1 for segmentation.", "tech_highlights": [ "Muse Spark", "SAM 3.1 Vision", "Next.js + Supabase" ], "created_at": "2026-10-27T13:30:18Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 122, "commits_before_window": 0, "prs_total": 50, "prs_merged": 50, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": true, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": true, "live_urls": [ "https://basa-chi.vercel.app" ], "anti_project_flag": "Banned Medical / Health Advisor", "is_disqualified": true, "stars": 0, "score_impact": 2.2, "score_meta_tooling": 1.1, "score_tech_depth": 1.9, "score_demo": 1.4, "score_total": 2.64, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "High-impact domain", "+0.4" ], [ "Eval & benchmark proof", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (122)", "+0.6" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Agent / eval harness", "+0.2" ], [ "PR review workflow (50 PRs)", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Live web deployment", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 805, "is_new": true, "commits_delta": 122, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "moruku36/meta-global-ai-hackathon-trifecta-checker", "html_url": "https://github.com/moruku36/meta-global-ai-hackathon-trifecta-checker", "track": "Push the Frontier", "domain": "Developer Tooling, Infra & Security", "summary": "Pre-flight safety checker for risky AI agent capability combos", "readme_summary": "Chat-first diagnostic with Trafica that analyzes agent descriptions or MCP configs for lethal trifecta risk. Explains why combos are unsafe and how to split capabilities. Multilingual app with live Vercel demo.", "tech_highlights": [ "Agent Safety Check", "MCP Config Analysis", "Vercel App" ], "created_at": "2026-10-26T22:15:04Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 57, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": true, "has_tests": true, "has_src": false, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": true, "live_urls": [ "https://meta-global-ai-hackathon-trifecta-c.vercel.app/", "https://meta-global-ai-hackathon-trifecta-c.vercel.app" ], "anti_project_flag": "Medical Advice / Diagnostic (Banned Anti-Project)", "is_disqualified": true, "stars": 0, "score_impact": 2.7, "score_meta_tooling": 1.3, "score_tech_depth": 1.2, "score_demo": 1.4, "score_total": 2.64, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "High-impact domain", "+0.4" ], [ "Docker packaging", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (57)", "+0.6" ], [ "Automated test suite", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Live web deployment", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 806, "is_new": false, "commits_delta": 6, "rank_delta": -349, "commits_delta_last_run": 0 }, { "full_name": "Rashad-Mohammed02/iris", "html_url": "https://github.com/Rashad-Mohammed02/iris", "track": "Build for Your World", "domain": "General & Emerging Applications", "summary": "Daily AI notes keep you close to your 5 people with private, shareable updates", "readme_summary": "Iris sends short daily updates to 5 close contacts with one actionable idea, hiding private context. Built with Python engine + web UI, it runs entirely on Muse Spark 1.3 via Meta Model API for filtering and note generation.", "tech_highlights": [ "Muse Spark 1.3", "Privacy Filtering", "Python + Web UI" ], "created_at": "2026-10-29T14:06:12Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 53, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": true, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": true, "live_urls": [ "https://rashad-mohammed02.github.io/iris/" ], "anti_project_flag": "Banned Medical / Health Advisor", "is_disqualified": true, "stars": 0, "score_impact": 1.7, "score_meta_tooling": 1.8, "score_tech_depth": 1.7, "score_demo": 1.4, "score_total": 2.64, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "General domain", "+0.2" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (53)", "+0.6" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Automated CI workflow", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Live web deployment", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 807, "is_new": true, "commits_delta": 53, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "msalihk/anyone-hear-me", "html_url": "https://github.com/msalihk/anyone-hear-me", "track": "Build for Your World", "domain": "Healthcare, Civic Tech & Sustainability", "summary": "Disaster agent turning voice notes and posts into deduplicated rescue tasks", "readme_summary": "Earthquake-response agent that transcribes voice notes with Muse Voice Transcribe biased to district place-names. Muse Spark reads Turkish/Arabic messages to extract and deduplicate rescue tasks for coordinators. Dockerized Python service with tests.", "tech_highlights": [ "Muse Voice Transcribe", "Muse Spark", "Docker + Python" ], "created_at": "2026-10-27T08:34:00Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 20, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": true, "has_tests": true, "has_src": true, "has_ci": true, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": true, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Banned Medical / Health Advisor", "is_disqualified": true, "stars": 0, "score_impact": 2.3, "score_meta_tooling": 1.8, "score_tech_depth": 1.5, "score_demo": 1.0, "score_total": 2.64, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "High-impact domain", "+0.4" ], [ "Docker packaging", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ], [ "Open-weights / fine-tuning", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (20)", "+0.4" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Automated CI workflow", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 808, "is_new": false, "commits_delta": 0, "rank_delta": -310, "commits_delta_last_run": 0 }, { "full_name": "seegongsik/anchor-orbit-risk", "html_url": "https://github.com/seegongsik/anchor-orbit-risk", "track": "Build for Your World", "domain": "Multimodal Vision & Video (SAM / Vision)", "summary": "Phone-photo workplace toppling risk assessment with measured fall energy", "readme_summary": "Measures toppling distance and fall energy from one phone photo using gravity sensor and SAM 3.1 segmentation. Muse Spark Open drafts likelihood, severity and controls from tool-call numbers only. Supervisor confirms all grades; checker blocks model-typed numbers.", "tech_highlights": [ "SAM 3.1 Vision", "Muse Spark Open", "Phone Sensors + Physics" ], "created_at": "2026-10-26T13:42:55Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 7, "commits_before_window": 0, "prs_total": 3, "prs_merged": 2, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": true, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": true, "live_urls": [ "https://anchor-orbit-risk.vercel.app" ], "anti_project_flag": "Banned Medical / Health Advisor", "is_disqualified": true, "stars": 0, "score_impact": 1.8, "score_meta_tooling": 2.3, "score_tech_depth": 1.1, "score_demo": 1.4, "score_total": 2.64, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ], [ "Open-weights / fine-tuning", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "5+ window commits (7)", "+0.2" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Live web deployment", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 809, "is_new": false, "commits_delta": 0, "rank_delta": -283, "commits_delta_last_run": 0 }, { "full_name": "mherick/aidrelay", "html_url": "https://github.com/mherick/aidrelay", "track": "Build for Your World", "domain": "Healthcare, Civic Tech & Sustainability", "summary": "Offline-first casualty relay that structures dictated care for dispatch boards", "readme_summary": "PWA where responders dictate care given, confirm structured records, and relay to a red-first dispatch board. Offline-first vanilla JS with on-device encryption, no backend, uses Meta AI for structuring.", "tech_highlights": [ "Offline-first PWA", "On-device Encryption", "Meta AI Structuring" ], "created_at": "2026-10-31T15:52:38Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 5, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": false, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": true, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": true, "video_urls": [ "https://youtu.be/LUchtA-aDk8" ], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Banned Medical / Health Advisor", "is_disqualified": true, "stars": 0, "score_impact": 1.9, "score_meta_tooling": 1.8, "score_tech_depth": 0.8, "score_demo": 2.1, "score_total": 2.64, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "High-impact domain", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "Open-weights / fine-tuning", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "5+ window commits (5)", "+0.2" ], [ "Automated test suite", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Video walkthrough", "+1.1" ], [ "Reproducible setup guide", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 810, "is_new": true, "commits_delta": 5, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "dangkhoa241/ClimateGuard", "html_url": "https://github.com/dangkhoa241/ClimateGuard", "track": "Build for Your World", "domain": "Healthcare, Civic Tech & Sustainability", "summary": "Multilingual weather, air alerts plus photo damage reports for farmworkers", "readme_summary": "Polls NWS and AirNow every 15 minutes for localized alerts translated to user language with low-literacy UI. Photo damage flow outlined by SAM 3.1 for paperwork help. SAM frontend plus backend template, built solo with Muse Spark and Copilot assistance.", "tech_highlights": [ "Muse Spark", "SAM 3.1 Vision", "NWS + AirNow API" ], "created_at": "2026-10-26T20:32:22Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 82, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": true, "has_ci": true, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": true, "live_urls": [ "https://climate-guard-khaki.vercel.app", "https://climate-guard-khaki.vercel.app/?demo=1" ], "anti_project_flag": "Banned Medical / Health Advisor", "is_disqualified": true, "stars": 0, "score_impact": 1.9, "score_meta_tooling": 1.8, "score_tech_depth": 1.4, "score_demo": 1.4, "score_total": 2.6, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "High-impact domain", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (82)", "+0.6" ], [ "Modular src/ architecture", "+0.3" ], [ "Automated CI workflow", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Live web deployment", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 811, "is_new": false, "commits_delta": 41, "rank_delta": -361, "commits_delta_last_run": 0 }, { "full_name": "danny121583/traceforge", "html_url": "https://github.com/danny121583/traceforge", "track": "Push the Frontier", "domain": "Education & Knowledge Systems", "summary": "Virtual electronics bench for practicing circuit diagnosis on simulated faulty boards", "readme_summary": "Hardware-free lab with deterministic MNA solver, hidden fault injection and virtual multimeter on three boards. Provides datasheet-grounded AI diagnosis, scoring against withheld ground truth. Includes autonomy benchmark docs and web workbench UI.", "tech_highlights": [ "MNA Circuit Solver", "AI Diagnosis Scoring", "Virtual Multimeter" ], "created_at": "2026-10-27T00:28:32Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 27, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": true, "live_urls": [ "https://traceforge-mcp-staging.apd1034.workers.dev/mcp`", "https://traceforge-ten.vercel.app" ], "anti_project_flag": "Medical Advice / Diagnostic (Banned Anti-Project)", "is_disqualified": true, "stars": 0, "score_impact": 2.2, "score_meta_tooling": 1.6, "score_tech_depth": 1.3, "score_demo": 1.4, "score_total": 2.6, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "Domain alignment", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (27)", "+0.4" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Live web deployment", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 812, "is_new": false, "commits_delta": 0, "rank_delta": -375, "commits_delta_last_run": 0 }, { "full_name": "hyggg222/meta-hackathon-2026", "html_url": "https://github.com/hyggg222/meta-hackathon-2026", "track": "Build for Your World", "domain": "General & Emerging Applications", "summary": "Placeholder indie hackathon repo with no defined project yet.", "readme_summary": "Repository contains only a README stating build period Oct 27-Nov 4 2026 and that project description is coming soon. No stack, architecture, or Meta AI / Muse usage is documented; all project code is stated to be written during the hackathon.", "tech_highlights": [], "created_at": "2026-10-26T21:43:36Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 5, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": false, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.2, "score_meta_tooling": 0.5, "score_tech_depth": 0.5, "score_demo": 0.4, "score_total": 2.6, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "General domain", "+0.2" ] ], "meta": [ [ "Base", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "5+ window commits (5)", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ] ] }, "rank": 813, "is_new": false, "commits_delta": 3, "rank_delta": -342, "commits_delta_last_run": 0 }, { "full_name": "richyboy035/lumen", "html_url": "https://github.com/richyboy035/lumen", "track": "Build for Your World", "domain": "Healthcare, Civic Tech & Sustainability", "summary": "AI power assistant for managing Nigerian home energy use", "readme_summary": "Lumen is an AI assistant for Nigerian homes built for the Meta hackathon. Aims to help with power management. No stack detailed in README, built on Meta AI models.", "tech_highlights": [ "Energy assistant", "Nigeria homes", "Meta AI" ], "created_at": "2026-10-26T10:18:22Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 1, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": false, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.4, "score_meta_tooling": 0.5, "score_tech_depth": 0.3, "score_demo": 0.4, "score_total": 2.6, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "High-impact domain", "+0.4" ] ], "meta": [ [ "Base", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ] ] }, "rank": 814, "is_new": false, "commits_delta": 0, "rank_delta": -338, "commits_delta_last_run": 0 }, { "full_name": "marts-dev/GarbageTrack", "html_url": "https://github.com/marts-dev/GarbageTrack", "track": "Build for Your World", "domain": "Healthcare, Civic Tech & Sustainability", "summary": "Waste tracking app for reporting and managing garbage", "readme_summary": "GarbageTrack is a Meta Hackathon 2026 project for waste tracking. README and tree are minimal with no stack disclosed. Intended for civic waste reporting and sustainability workflows.", "tech_highlights": [ "Waste tracking", "Civic tech", "Meta AI" ], "created_at": "2026-10-27T01:01:45Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 1, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": false, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.4, "score_meta_tooling": 0.5, "score_tech_depth": 0.3, "score_demo": 0.4, "score_total": 2.6, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "High-impact domain", "+0.4" ] ], "meta": [ [ "Base", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ] ] }, "rank": 815, "is_new": false, "commits_delta": 0, "rank_delta": -328, "commits_delta_last_run": 0 }, { "full_name": "kruthikvarshan/meta-global-ai-hackathon-dashboard", "html_url": "https://github.com/kruthikvarshan/meta-global-ai-hackathon-dashboard", "track": "Build for Your World", "domain": "Autonomous Agents & Workflow Automation", "summary": "GroupChat layer turning group chats into tasks and deadlines", "readme_summary": "GroupChat OS extracts decisions, tasks, payment promises and deadlines from chaotic group chats. README describes product concept for coordinated action via dashboard. No tech stack or Muse model usage detailed yet.", "tech_highlights": [ "Group Chat Parsing", "Task Extraction", "Hackathon Dashboard" ], "created_at": "2026-10-27T16:01:35Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 1, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": false, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.4, "score_meta_tooling": 0.5, "score_tech_depth": 0.3, "score_demo": 0.4, "score_total": 2.6, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "High-impact domain", "+0.4" ] ], "meta": [ [ "Base", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ] ] }, "rank": 816, "is_new": true, "commits_delta": 1, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "Flying-Sailor2306/fleet-ops-ai", "html_url": "https://github.com/Flying-Sailor2306/fleet-ops-ai", "track": "Build for Your World", "domain": "Autonomous Agents & Workflow Automation", "summary": "Multi-agent prototype for fleet operations management", "readme_summary": "Described as a multi-agent fleet operations prototype for the hackathon. Repo contains only README with no code, architecture, or demo details. No Meta AI / Muse usage specified.", "tech_highlights": [ "Multi-Agent Concept", "Fleet Operations" ], "created_at": "2026-10-31T23:12:04Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 1, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": false, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.4, "score_meta_tooling": 0.5, "score_tech_depth": 0.3, "score_demo": 0.4, "score_total": 2.6, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "High-impact domain", "+0.4" ] ], "meta": [ [ "Base", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ] ] }, "rank": 817, "is_new": true, "commits_delta": 1, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "HusseinAdeiza/sanitova-lens-website", "html_url": "https://github.com/HusseinAdeiza/sanitova-lens-website", "track": "Build for Your World", "domain": "Healthcare, Civic Tech & Sustainability", "summary": "Visual pre-screen tool that flags visible WASH facility issues before inspections", "readme_summary": "Sanitova Lens is a static website for visible-conditions pre-screening of WASH facilities. Built with HTML and static assets hosted via .nojekyll. It presents a front-end concept for water, sanitation and hygiene checks.", "tech_highlights": [ "Static HTML Site", "WASH Pre-screen UI" ], "created_at": "2026-11-01T21:45:27Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 1, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": false, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.4, "score_meta_tooling": 0.5, "score_tech_depth": 0.3, "score_demo": 0.4, "score_total": 2.6, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "High-impact domain", "+0.4" ] ], "meta": [ [ "Base", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ] ] }, "rank": 818, "is_new": true, "commits_delta": 1, "rank_delta": 0, "commits_delta_last_run": 1 }, { "full_name": "KarlaPocasangre/aegis-home", "html_url": "https://github.com/KarlaPocasangre/aegis-home", "track": "Build for Your World", "domain": "Healthcare, Civic Tech & Sustainability", "summary": "Spanish-first app turning home photos into fall-prevention safety plans", "readme_summary": "Web app that converts photos of older adults homes into visual prioritized locally-costed fixes. Stack is Node API plus web client using Meta Muse Spark and SAM 3.1 for vision analysis.", "tech_highlights": [ "SAM 3.1 Vision", "Muse Spark", "Node + Vercel" ], "created_at": "2026-10-31T22:28:37Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 55, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": true, "has_ci": true, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": true, "live_urls": [ "https://client-eight-psi-67.vercel.app", "https://aegis-home-api.onrender.com/health" ], "anti_project_flag": "Banned Medical / Health Advisor", "is_disqualified": true, "stars": 0, "score_impact": 1.9, "score_meta_tooling": 1.6, "score_tech_depth": 1.4, "score_demo": 1.4, "score_total": 2.52, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "High-impact domain", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (55)", "+0.6" ], [ "Modular src/ architecture", "+0.3" ], [ "Automated CI workflow", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Live web deployment", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 819, "is_new": true, "commits_delta": 55, "rank_delta": 0, "commits_delta_last_run": 13 }, { "full_name": "sholaola23/meta-hackathon-2026", "html_url": "https://github.com/sholaola23/meta-hackathon-2026", "track": "Build for Your World", "domain": "Multimodal Vision & Video (SAM / Vision)", "summary": "Snap a market stall and voice prices to get a WhatsApp catalogue", "readme_summary": "StallSnap segments stall photos with SAM 3.1 to cut out products and transcribes Pidgin voice notes with Muse Voice to price items. Generates shareable catalogue for WhatsApp traders. Node/bun + src stack with test materials and build log.", "tech_highlights": [ "SAM 3.1 Vision", "Muse Voice AI", "WhatsApp Catalogue" ], "created_at": "2026-10-26T08:11:01Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 24, "commits_before_window": 0, "prs_total": 11, "prs_merged": 11, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": true, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Banned AI Job Screener", "is_disqualified": true, "stars": 0, "score_impact": 1.8, "score_meta_tooling": 1.8, "score_tech_depth": 1.7, "score_demo": 1.0, "score_total": 2.52, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (24)", "+0.4" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Automated CI workflow", "+0.2" ], [ "PR review workflow (11 PRs)", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 820, "is_new": false, "commits_delta": 0, "rank_delta": -295, "commits_delta_last_run": 0 }, { "full_name": "Erlansoo/Lunes", "html_url": "https://github.com/Erlansoo/Lunes", "track": "Push the Frontier", "domain": "Robotics, IoT & Manufacturing", "summary": "Bench assistant looks at circuit boards and tells you where to probe next", "readme_summary": "Lunes combines USB-microscope mosaics, SAM 3.1 component detection and instrument readings vs circuit simulation. Python + custom firmware drives bench CNC, using Meta models for diagnosis and next-measurement policy.", "tech_highlights": [ "SAM 3.1 Vision", "Bench CNC + Firmware", "Circuit Simulation" ], "created_at": "2026-10-27T17:56:42Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 17, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": true, "has_eval_benchmarks": false, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Medical Advice / Diagnostic (Banned Anti-Project)", "is_disqualified": true, "stars": 0, "score_impact": 2.1, "score_meta_tooling": 2.3, "score_tech_depth": 1.3, "score_demo": 0.6, "score_total": 2.52, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "High-impact domain", "+0.4" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ], [ "Open-weights / fine-tuning", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (17)", "+0.4" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 821, "is_new": false, "commits_delta": 12, "rank_delta": -281, "commits_delta_last_run": 0 }, { "full_name": "Johan-de-Beer/vouch-audit-evidence-agent", "html_url": "https://github.com/Johan-de-Beer/vouch-audit-evidence-agent", "track": "Build for Your World", "domain": "Legal & Compliance", "summary": "Audits purchase ledgers against invoices with pixel-backed evidence", "readme_summary": "Reviews ledger sample against invoices, POs and GRNs, linking findings to image crops and working papers. Offline synthetic demo with fixtures; live preflight verified Muse Spark extraction and SAM masking.", "tech_highlights": [ "SAM Vision", "Muse Spark 1.3", "Node.js + Baseten" ], "created_at": "2026-10-29T04:15:37Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 12, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": true, "has_tests": true, "has_src": true, "has_ci": true, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Banned Basic RAG", "is_disqualified": true, "stars": 0, "score_impact": 2.2, "score_meta_tooling": 1.8, "score_tech_depth": 1.3, "score_demo": 1.0, "score_total": 2.52, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Docker packaging", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ] ], "tech": [ [ "Base", "+0.3" ], [ "5+ window commits (12)", "+0.2" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Automated CI workflow", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 822, "is_new": false, "commits_delta": 7, "rank_delta": -328, "commits_delta_last_run": 0 }, { "full_name": "dantermz/kora-scribe", "html_url": "https://github.com/dantermz/kora-scribe", "track": "Build for Your World", "domain": "Healthcare, Civic Tech & Sustainability", "summary": "Hands-free scribe that turns glasses audio into doctor-signed SOAP notes.", "readme_summary": "Captures consultations via Ray-Ban Meta glasses, transcribes with Muse Voice Transcribe and drafts SOAP notes with Muse Glimmer. Verifier agent grounds every line in transcript for clinician review.", "tech_highlights": [ "Muse Voice Transcribe", "Muse Glimmer", "Muse Spark Open" ], "created_at": "2026-10-28T04:01:00Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 10, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": true, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": true, "has_eval_benchmarks": true, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Banned Medical / Health Advisor", "is_disqualified": true, "stars": 0, "score_impact": 2.0, "score_meta_tooling": 2.3, "score_tech_depth": 1.0, "score_demo": 1.0, "score_total": 2.52, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "High-impact domain", "+0.4" ], [ "Eval & benchmark proof", "+0.3" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ], [ "Open-weights / fine-tuning", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "5+ window commits (10)", "+0.2" ], [ "Modular src/ architecture", "+0.3" ], [ "Agent / eval harness", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 823, "is_new": false, "commits_delta": 6, "rank_delta": -275, "commits_delta_last_run": 0 }, { "full_name": "motdang/paid-from-anywhere", "html_url": "https://github.com/motdang/paid-from-anywhere", "track": "Build for Your World", "domain": "Finance, Crypto & Web3", "summary": "WhatsApp money desk helping nonprofits track donations from anywhere", "readme_summary": "WhatsApp-based money desk for nonprofits, started Oct 27 2026 for the hackathon Startup track. Repo currently holds only README with prior work isolated in prior/. Intends to use Meta AI on WhatsApp for nonprofit finance workflows.", "tech_highlights": [ "WhatsApp API", "Muse Models", "Nonprofit Fintech" ], "created_at": "2026-10-27T06:05:49Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 3, "commits_before_window": 0, "prs_total": 1, "prs_merged": 1, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": false, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.3, "score_meta_tooling": 0.5, "score_tech_depth": 0.3, "score_demo": 0.4, "score_total": 2.5, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ] ] }, "rank": 824, "is_new": false, "commits_delta": 0, "rank_delta": -359, "commits_delta_last_run": 0 }, { "full_name": "TheMunene/pesa-recon-agent", "html_url": "https://github.com/TheMunene/pesa-recon-agent", "track": "Build for Your World", "domain": "Finance, Crypto & Web3", "summary": "Reconciles M-Pesa, bank and paper records and explains mismatches plainly", "readme_summary": "Ingests M-Pesa PDF/CSV, bank exports and receipt photos for Kenyan small businesses. Matches payments, withdrawals and deposits to surface unpaid and unexplained items. Uses Meta AI to explain results in plain language.", "tech_highlights": [ "M-Pesa Reconciliation", "Document OCR", "Muse Models" ], "created_at": "2026-10-27T06:26:21Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 2, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": false, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 1, "score_impact": 1.3, "score_meta_tooling": 0.5, "score_tech_depth": 0.3, "score_demo": 0.4, "score_total": 2.5, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ] ] }, "rank": 825, "is_new": false, "commits_delta": 0, "rank_delta": -359, "commits_delta_last_run": 0 }, { "full_name": "LegitAgent/meta-cv-hackathon", "html_url": "https://github.com/LegitAgent/meta-cv-hackathon", "track": "Build for Your World", "domain": "Education & Knowledge Systems", "summary": "Turns phone, laptop or dog screenshots into beginner study guides with quizzes.", "readme_summary": "User uploads a screenshot; open-vocab detector finds phone/laptop/dog boxes for selection, then crops to a vision model for summary. Asks familiarity level, then generates Chapter 1 guide with sources and 3-question quiz. Proposes RAG for study-guide generation to avoid hallucinated sources.", "tech_highlights": [ "Open-Vocab Detection", "Vision-Language Model", "RAG Study Guide" ], "created_at": "2026-10-26T09:47:51Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 2, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": false, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.3, "score_meta_tooling": 0.5, "score_tech_depth": 0.3, "score_demo": 0.4, "score_total": 2.5, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ] ] }, "rank": 826, "is_new": false, "commits_delta": 1, "rank_delta": -334, "commits_delta_last_run": 0 }, { "full_name": "baobabtr33/meta-ai-hackathon-human-sign", "html_url": "https://github.com/baobabtr33/meta-ai-hackathon-human-sign", "track": "Build for Your World", "domain": "Multimodal Vision & Video (SAM / Vision)", "summary": "Placeholder repo hinting at a human-sign related AI project.", "readme_summary": "Repository contains only a README with the repeated project title and no functional description. No stack, architecture, or Muse / SAM usage is documented; intent is inferred only from the human-sign name.", "tech_highlights": [], "created_at": "2026-10-27T00:04:54Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 2, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": false, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.3, "score_meta_tooling": 0.5, "score_tech_depth": 0.3, "score_demo": 0.4, "score_total": 2.5, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ] ] }, "rank": 827, "is_new": false, "commits_delta": 0, "rank_delta": -355, "commits_delta_last_run": 0 }, { "full_name": "prabhatfulzelethings173129/MeCap", "html_url": "https://github.com/prabhatfulzelethings173129/MeCap", "track": "Build for Your World", "domain": "Finance, Crypto & Web3", "summary": "Personal market-cap app that lets users IPO themselves and track value", "readme_summary": "MeCap proposes a consumer concept to IPO yourself and track personal market cap. Repository contains only a README with no implemented stack. No explicit Meta AI / Muse integration is documented.", "tech_highlights": [ "Concept Prototype", "No Stack Yet" ], "created_at": "2026-10-31T13:35:24Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 2, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": false, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.3, "score_meta_tooling": 0.5, "score_tech_depth": 0.3, "score_demo": 0.4, "score_total": 2.5, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ] ] }, "rank": 828, "is_new": true, "commits_delta": 2, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "whiteeedev/ReScene", "html_url": "https://github.com/whiteeedev/ReScene", "track": "Build for Your World", "domain": "Multimodal Vision & Video (SAM / Vision)", "summary": "AI tool that reconstructs scenes from input images", "readme_summary": "ReScene is an AI scene reconstructor entered in the Meta hackathon. README and file tree are minimal with no stack disclosed. Appears to use Meta AI vision models for scene understanding.", "tech_highlights": [ "Vision AI", "Scene reconstruction", "Meta AI" ], "created_at": "2026-10-26T16:57:30Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 1, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": false, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 1, "score_impact": 1.3, "score_meta_tooling": 0.5, "score_tech_depth": 0.3, "score_demo": 0.4, "score_total": 2.5, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ] ] }, "rank": 829, "is_new": false, "commits_delta": 0, "rank_delta": -356, "commits_delta_last_run": 0 }, { "full_name": "copiloteLoading/deal-copilot", "html_url": "https://github.com/copiloteLoading/deal-copilot", "track": "Build for Your World", "domain": "Business, Sales & Commerce", "summary": "Voice-first copilot mapping stakeholders and win odds for deals", "readme_summary": "Private voice-first copilot for infrastructure deals turning debriefs into stakeholder maps. Uses Muse models for transcription and analysis with HMM for win probability. Privacy-focused workflow.", "tech_highlights": [ "Muse models", "Voice to insights", "HMM scoring" ], "created_at": "2026-10-27T22:10:06Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 1, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": false, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.3, "score_meta_tooling": 0.5, "score_tech_depth": 0.3, "score_demo": 0.4, "score_total": 2.5, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ] ] }, "rank": 830, "is_new": false, "commits_delta": 0, "rank_delta": -352, "commits_delta_last_run": 0 }, { "full_name": "Varun-Gupta0/MetaAiHackathonEventology", "html_url": "https://github.com/Varun-Gupta0/MetaAiHackathonEventology", "track": "Build for Your World", "domain": "Business, Sales & Commerce", "summary": "Event management concept repo with no implemented code yet", "readme_summary": "Placeholder repo containing only LICENSE with no source, README, or file tree. Name suggests event planning or discovery app for hackathon. No tech stack or Meta model usage visible.", "tech_highlights": [ "Concept Stage", "Events App" ], "created_at": "2026-10-28T15:59:36Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 1, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": false, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.3, "score_meta_tooling": 0.5, "score_tech_depth": 0.3, "score_demo": 0.4, "score_total": 2.5, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ] ] }, "rank": 831, "is_new": false, "commits_delta": 0, "rank_delta": -348, "commits_delta_last_run": 0 }, { "full_name": "coursetec-ai/coursetec-hackathon", "html_url": "https://github.com/coursetec-ai/coursetec-hackathon", "track": "Build for Your World", "domain": "Education & Knowledge Systems", "summary": "Course creation demo slice prepared for hackathon judging snapshot", "readme_summary": "CourseTec demo slice for the Meta Global AI Developer Hackathon 2026. Repository currently contains only a README placeholder with full snapshot due Nov 4. CourseTec 1.x is noted as disclosed prior work.", "tech_highlights": [ "Education Platform", "Muse Models" ], "created_at": "2026-10-28T02:33:14Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 1, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": false, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.3, "score_meta_tooling": 0.5, "score_tech_depth": 0.3, "score_demo": 0.4, "score_total": 2.5, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ] ] }, "rank": 832, "is_new": false, "commits_delta": 0, "rank_delta": -342, "commits_delta_last_run": 0 }, { "full_name": "jeankpoti/echovoiice-assistant", "html_url": "https://github.com/jeankpoti/echovoiice-assistant", "track": "Build for Your World", "domain": "Voice, Speech & Audio AI", "summary": "Voice assistant that speaks and replies in Ewe and African languages", "readme_summary": "Conversational voice assistant for African languages with Ewe speech in and out. Uses Meta Muse Spark for dialogue and EchoVoiice for text-to-speech. Repo tree shows only LICENSE, no implementation files yet.", "tech_highlights": [ "Muse Spark 1.3", "EchoVoiice TTS", "Ewe Voice AI" ], "created_at": "2026-10-29T08:20:28Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 1, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": false, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.3, "score_meta_tooling": 0.5, "score_tech_depth": 0.3, "score_demo": 0.4, "score_total": 2.5, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ] ] }, "rank": 833, "is_new": true, "commits_delta": 1, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "razeenjubair744-png/AI-powered-fashion-shopping-and-autonomous-retail-marketing", "html_url": "https://github.com/razeenjubair744-png/AI-powered-fashion-shopping-and-autonomous-retail-marketing", "track": "Build for Your World", "domain": "Business, Sales & Commerce", "summary": "AI fashion shopping assistant with autonomous retail marketing", "readme_summary": "Project aims at AI-powered fashion shopping and autonomous retail marketing. Repo contains only LICENSE and placeholder README with no architecture. Intended Meta AI integration is not yet documented.", "tech_highlights": [ "Retail AI", "Fashion Commerce" ], "created_at": "2026-10-30T04:38:44Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 1, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": false, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.3, "score_meta_tooling": 0.5, "score_tech_depth": 0.3, "score_demo": 0.4, "score_total": 2.5, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ] ] }, "rank": 834, "is_new": true, "commits_delta": 1, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "Dhool143/medina-academy-hackathon", "html_url": "https://github.com/Dhool143/medina-academy-hackathon", "track": "Build for Your World", "domain": "Education & Knowledge Systems", "summary": "Teacher tool that drafts K-6 learning activities from topic and grade", "readme_summary": "Medina Academy is a planned teacher tool for K-6 learning activities. Teacher enters topic and grade, a Meta AI model drafts an editable activity. Being built Oct 26-Nov 4, code not yet present.", "tech_highlights": [ "Meta AI Drafting", "K-6 EdTech", "Teacher Tool" ], "created_at": "2026-10-27T17:45:56Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 1, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": false, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.3, "score_meta_tooling": 0.5, "score_tech_depth": 0.3, "score_demo": 0.4, "score_total": 2.5, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ] ] }, "rank": 835, "is_new": true, "commits_delta": 1, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "scoobydoobydrew/meta_ai_hackathon", "html_url": "https://github.com/scoobydoobydrew/meta_ai_hackathon", "track": "Push the Frontier", "domain": "Healthcare, Civic Tech & Sustainability", "summary": "LLM proposes cell-signalling rules that solvers formally verify for lab testing", "readme_summary": "CellProof repairs a 30-node Boolean DNA-damage model (Gupta 2023). Python stack with clingo, mpbn, AEON, pyboolnet for verification; LLM reads papers to propose rules. Prioritizes hypotheses for lab testing, no medical advice.", "tech_highlights": [ "Muse LLM proposals", "clingo + mpbn solver", "Python Boolean nets" ], "created_at": "2026-10-29T04:24:32Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 34, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Banned Medical / Health Advisor", "is_disqualified": true, "stars": 0, "score_impact": 2.3, "score_meta_tooling": 1.6, "score_tech_depth": 1.3, "score_demo": 1.0, "score_total": 2.48, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "High-impact domain", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (34)", "+0.4" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 836, "is_new": false, "commits_delta": 32, "rank_delta": -368, "commits_delta_last_run": 0 }, { "full_name": "SapSaeta/relief-net", "html_url": "https://github.com/SapSaeta/relief-net", "track": "Build for Your World", "domain": "Healthcare, Civic Tech & Sustainability", "summary": "Turns disaster phone video into prioritized evidence-backed help requests for coordinators", "readme_summary": "Next.js TypeScript app on Vercel that converts phone video of damage to triaged requests with human approval. Uses Muse Spark 1.3 for reasoning, SAM 3.1 for image segmentation, and Muse Voice Transcribe 1.0 for audio.", "tech_highlights": [ "Muse Spark 1.3", "SAM 3.1", "Next.js + Vercel" ], "created_at": "2026-10-26T20:08:29Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 39, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": true, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": true, "live_urls": [ "https://relief-net-one.vercel.app", "https://relief-net-one.vercel.app/audit" ], "anti_project_flag": "Banned Medical / Health Advisor", "is_disqualified": true, "stars": 0, "score_impact": 1.9, "score_meta_tooling": 1.8, "score_tech_depth": 1.0, "score_demo": 1.4, "score_total": 2.44, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "High-impact domain", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (39)", "+0.4" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Live web deployment", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 837, "is_new": false, "commits_delta": 22, "rank_delta": -729, "commits_delta_last_run": 8 }, { "full_name": "adityadixit07/insaaf", "html_url": "https://github.com/adityadixit07/insaaf", "track": "Build for Your World", "domain": "Legal & Compliance", "summary": "Verifies gig workers' evidence photos and drafts ready-to-submit dispute appeals", "readme_summary": "Next.js app for penalized gig workers to contest pay cuts and strikes. Uses SAM 3.1 to verify evidence photos, Muse Spark to draft appeals, and Muse Voice Transcribe for input.", "tech_highlights": [ "SAM 3.1 Vision", "Muse Spark", "Muse Voice Transcribe" ], "created_at": "2026-10-26T15:30:54Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 5, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": true, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": false, "has_video_demo": true, "video_urls": [ "https://youtu.be/VIDEO_ID" ], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Banned Basic RAG", "is_disqualified": true, "stars": 0, "score_impact": 1.8, "score_meta_tooling": 1.8, "score_tech_depth": 0.8, "score_demo": 1.7, "score_total": 2.44, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ] ], "tech": [ [ "Base", "+0.3" ], [ "5+ window commits (5)", "+0.2" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Video walkthrough", "+1.1" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 838, "is_new": false, "commits_delta": 1, "rank_delta": -380, "commits_delta_last_run": 0 }, { "full_name": "bgSunil/share-and-earn-ai", "html_url": "https://github.com/bgSunil/share-and-earn-ai", "track": "Build for Your World", "domain": "Business, Sales & Commerce", "summary": "WhatsApp referral layer that rewards trusted friend-to-friend recommendations.", "readme_summary": "Share & Earn AI adds AI features to Share & Earn Lite, a QR-based rating and named-friend referral system for local shops. Stack is React TypeScript with Firebase Firestore and Cloud Functions. Planned Meta AI use for review insights, fraud-safe recommendations and owner feedback.", "tech_highlights": [ "React + Firebase", "WhatsApp Deep Links", "Meta AI Integration" ], "created_at": "2026-10-25T20:07:04Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 9, "commits_before_window": 14, "prs_total": 0, "prs_merged": 0, "is_preexisting": true, "has_docker": false, "has_tests": false, "has_src": false, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.3, "score_meta_tooling": 0.5, "score_tech_depth": 0.2, "score_demo": 0.4, "score_total": 2.4, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "5+ window commits (9)", "+0.2" ], [ "Pre-Oct 26 commits dominate (14)", "-0.3" ] ], "demo": [ [ "Base", "+0.4" ] ] }, "rank": 839, "is_new": false, "commits_delta": 0, "rank_delta": -388, "commits_delta_last_run": 0 }, { "full_name": "IAMMOJAHID/SpotCool-AI", "html_url": "https://github.com/IAMMOJAHID/SpotCool-AI", "track": "Build for Your World", "domain": "General & Emerging Applications", "summary": "Placeholder hackathon repo named SpotCool-AI with no details yet", "readme_summary": "Repo titled SpotCool-AI listed as a Meta Global AI Hackathon project. README contains only a one-line placeholder with no stack or architecture. No Meta AI integration details are documented.", "tech_highlights": [ "Undocumented Stack" ], "created_at": "2026-10-31T13:42:13Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 1, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": false, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 1, "score_impact": 1.2, "score_meta_tooling": 0.5, "score_tech_depth": 0.3, "score_demo": 0.4, "score_total": 2.4, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "General domain", "+0.2" ] ], "meta": [ [ "Base", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ] ] }, "rank": 840, "is_new": true, "commits_delta": 1, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "BW6Z/Repod", "html_url": "https://github.com/BW6Z/Repod", "track": "Build for Your World", "domain": "General & Emerging Applications", "summary": "Placeholder hackathon repo named Repod with no details yet", "readme_summary": "Repo named Repod listed as a Meta Global AI Developer Hackathon project. README contains only a one-line placeholder. No stack, architecture, or Meta AI usage is documented.", "tech_highlights": [ "Undocumented Stack" ], "created_at": "2026-10-30T19:24:05Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 1, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": false, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.2, "score_meta_tooling": 0.5, "score_tech_depth": 0.3, "score_demo": 0.4, "score_total": 2.4, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "General domain", "+0.2" ] ], "meta": [ [ "Base", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ] ] }, "rank": 841, "is_new": true, "commits_delta": 1, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "mhussam-ai/SpotCool-AI", "html_url": "https://github.com/mhussam-ai/SpotCool-AI", "track": "Build for Your World", "domain": "General & Emerging Applications", "summary": "Placeholder hackathon repo named SpotCool-AI with no details yet", "readme_summary": "Repo titled SpotCool-AI listed as a meta Global AI Hackathon project. README contains only a one-line placeholder with no stack or architecture. No Meta AI integration details are documented.", "tech_highlights": [ "Undocumented Stack" ], "created_at": "2026-10-30T22:42:34Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 1, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": false, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Clear", "is_disqualified": false, "stars": 0, "score_impact": 1.2, "score_meta_tooling": 0.5, "score_tech_depth": 0.3, "score_demo": 0.4, "score_total": 2.4, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "General domain", "+0.2" ] ], "meta": [ [ "Base", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ] ] }, "rank": 842, "is_new": true, "commits_delta": 1, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "Huskyauto/pause-and-nourish", "html_url": "https://github.com/Huskyauto/pause-and-nourish", "track": "Build for Your World", "domain": "Healthcare, Civic Tech & Sustainability", "summary": "Voice-first PWA that guides a 2-minute pause and check-in during food cravings", "readme_summary": "Voice-first local-first PWA with Notice-Pause-Choose flow and live model-generated spoken dialogue. Built with Next.js/TypeScript as PWA using Meta Model API (Muse Spark/Wonder/Image, SAM 3.1) for personalized coaching. Wellness info only, no medical advice.", "tech_highlights": [ "Muse Spark + Wonder", "Next.js PWA", "Voice-first dialogue" ], "created_at": "2026-10-26T15:19:17Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 55, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": true, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": true, "live_urls": [ "https://pause-and-nourish.vercel.app" ], "anti_project_flag": "Banned Medical / Health Advisor", "is_disqualified": true, "stars": 0, "score_impact": 1.9, "score_meta_tooling": 1.8, "score_tech_depth": 1.2, "score_demo": 1.0, "score_total": 2.36, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "High-impact domain", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (55)", "+0.6" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Live web deployment", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 843, "is_new": false, "commits_delta": 50, "rank_delta": -300, "commits_delta_last_run": 3 }, { "full_name": "henryweimd/cozy-clinic", "html_url": "https://github.com/henryweimd/cozy-clinic", "track": "Build for Your World", "domain": "Healthcare, Civic Tech & Sustainability", "summary": "Cozy clinic game where persistent patients remember you and teach clinical reasoning", "readme_summary": "Browser portrait game where encounters change persistent patients across clinicians. Built with web frontend plus Supabase backend on Vercel. Uses Meta AI / Muse models to drive patient dialogue, memory, and clinical teaching.", "tech_highlights": [ "Muse Models", "Supabase + Vercel", "Mobile Web Game" ], "created_at": "2026-10-28T02:45:48Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 174, "commits_before_window": 0, "prs_total": 1, "prs_merged": 1, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": true, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": true, "live_urls": [ "https://cozy-clinic.vercel.app/", "https://cozy-clinic.vercel.app" ], "anti_project_flag": "Banned Medical / Health Advisor", "is_disqualified": true, "stars": 0, "score_impact": 1.9, "score_meta_tooling": 1.3, "score_tech_depth": 1.2, "score_demo": 1.4, "score_total": 2.32, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "High-impact domain", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (174)", "+0.6" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Live web deployment", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 844, "is_new": true, "commits_delta": 174, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "umdis/glosa", "html_url": "https://github.com/umdis/glosa", "track": "Build for Your World", "domain": "Education & Knowledge Systems", "summary": "Turns long lectures and sermons into searchable text with exact video citations.", "readme_summary": "Ingests hours of talks to enable search by what was said and shown, returning answers linked to verified timestamps. Dockerized pipeline with docs and specs for study workflows. Uses Meta transcription, vision and Muse models for grounding.", "tech_highlights": [ "Video to Footnotes", "Timestamp Grounding", "Docker + Transcripts" ], "created_at": "2026-10-29T02:03:44Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 43, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": true, "has_tests": true, "has_src": true, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Banned Basic RAG", "is_disqualified": true, "stars": 0, "score_impact": 2.2, "score_meta_tooling": 1.3, "score_tech_depth": 1.3, "score_demo": 1.0, "score_total": 2.32, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Docker packaging", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (43)", "+0.4" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 845, "is_new": false, "commits_delta": 7, "rank_delta": -348, "commits_delta_last_run": 0 }, { "full_name": "caudillsabastian6-png/card-cauldron-tcg", "html_url": "https://github.com/caudillsabastian6-png/card-cauldron-tcg", "track": "Build for Your World", "domain": "Multimodal Vision & Video (SAM / Vision)", "summary": "Trading-card authenticity checker that shows evidence or says unsure", "readme_summary": "Static web app that reads structured card crops with Muse Spark and Muse Wonder for authenticity verdicts. Shows evidence UI with demo, bulk and grading modes, preferring Inconclusive over guessing.", "tech_highlights": [ "Muse Spark Vision", "Muse Wonder Reads", "Static Web + Worker" ], "created_at": "2026-10-27T21:58:36Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 204, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": false, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": true, "live_urls": [ "https://cardcauldrontcg.com/demo" ], "anti_project_flag": "Banned Simple Image Analyzer", "is_disqualified": true, "stars": 0, "score_impact": 1.8, "score_meta_tooling": 1.6, "score_tech_depth": 0.9, "score_demo": 1.4, "score_total": 2.28, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (204)", "+0.6" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Live web deployment", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 846, "is_new": true, "commits_delta": 204, "rank_delta": 0, "commits_delta_last_run": 3 }, { "full_name": "NadyKor15/billradar", "html_url": "https://github.com/NadyKor15/billradar", "track": "Build for Your World", "domain": "Healthcare, Civic Tech & Sustainability", "summary": "Tool tracking legislative bills with samples and evaluations.", "readme_summary": "Tool tracking legislative bills with samples and evaluations.", "tech_highlights": [], "created_at": "2026-10-26T15:20:42Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 101, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": false, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": true, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Banned Medical / Health Advisor", "is_disqualified": true, "stars": 0, "score_impact": 1.7, "score_meta_tooling": 1.8, "score_tech_depth": 1.4, "score_demo": 0.8, "score_total": 2.28, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "High-impact domain", "+0.4" ], [ "Eval & benchmark proof", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (101)", "+0.6" ], [ "Automated test suite", "+0.3" ], [ "Agent / eval harness", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ] ] }, "rank": 847, "is_new": false, "commits_delta": 0, "rank_delta": -309, "commits_delta_last_run": 0 }, { "full_name": "TurabDevs/localdub", "html_url": "https://github.com/TurabDevs/localdub", "track": "Build for Your World", "domain": "Voice, Speech & Audio AI", "summary": "Dubs Hindi/Urdu videos to English with cloned voices and original background sound.", "readme_summary": "LocalDub pipeline transcribes, translates, and re-voices Hindi/Urdu video in English per character. Runs on free Kaggle CPU with Python pipeline and preserves music via source separation. Uses Muse Glimmer, Omnilingual ASR, and Demucs open weights.", "tech_highlights": [ "Omnilingual ASR", "Muse Glimmer", "Voice Cloning" ], "created_at": "2026-10-29T11:45:24Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 76, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": false, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": true, "has_eval_benchmarks": false, "has_setup_guide": false, "has_video_demo": true, "video_urls": [ "https://github.com/TurabDevs/localdub/releases/download/demo-v2/localdub_demo_v5.mp4", "https://github.com/TurabDevs/localdub/releases/download/demo-v2/aib_depression_en_v6.webm" ], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Banned Medical / Health Advisor", "is_disqualified": true, "stars": 0, "score_impact": 1.6, "score_meta_tooling": 1.3, "score_tech_depth": 0.9, "score_demo": 1.7, "score_total": 2.2, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "Open-weights / fine-tuning", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (76)", "+0.6" ] ], "demo": [ [ "Base", "+0.4" ], [ "Video walkthrough", "+1.1" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 848, "is_new": true, "commits_delta": 76, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "rajakumaranaap-rgb/makkal-agent-ai", "html_url": "https://github.com/rajakumaranaap-rgb/makkal-agent-ai", "track": "Build for Your World", "domain": "Healthcare, Civic Tech & Sustainability", "summary": "WhatsApp civic agent for Tamil Nadu entitlements and citizen actions", "readme_summary": "Autonomous multimodal agent for civic entitlements via WhatsApp Cloud API and web app. Uses Muse Spark, Muse Wonder and SAM 3.1 with knowledge base and action executor. Deployed on AWS EC2 with document auditing and test suite.", "tech_highlights": [ "Muse Spark + Wonder", "SAM 3.1 Vision", "WhatsApp Cloud API" ], "created_at": "2026-10-26T16:33:33Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 7, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": false, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Banned Medical / Health Advisor", "is_disqualified": true, "stars": 0, "score_impact": 1.9, "score_meta_tooling": 1.8, "score_tech_depth": 0.8, "score_demo": 1.0, "score_total": 2.2, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "High-impact domain", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ] ], "tech": [ [ "Base", "+0.3" ], [ "5+ window commits (7)", "+0.2" ], [ "Automated test suite", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 849, "is_new": false, "commits_delta": 0, "rank_delta": -318, "commits_delta_last_run": 0 }, { "full_name": "mtri0407/mesocycle", "html_url": "https://github.com/mtri0407/mesocycle", "track": "Build for Your World", "domain": "Healthcare, Civic Tech & Sustainability", "summary": "Voice-first life planner that protects sleep, health and relationships", "readme_summary": "Conversational planner where users describe their broken day and get a recovery-centered week plan. Built on Cloudflare Workers with docs and evals, deployed demo with 60-second trial. Uses Meta AI voice and Muse models for Call AI conversation and planning.", "tech_highlights": [ "Muse Models", "Voice AI Interface", "Cloudflare Workers" ], "created_at": "2026-10-27T06:28:12Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 47, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": true, "live_urls": [ "https://mesocycle.minhtriphamnguyen69.workers.dev", "https://mesocycle.minhtriphamnguyen69.workers.dev/privacy", "https://mesocycle.minhtriphamnguyen69.workers.dev/terms" ], "anti_project_flag": "Banned Medical / Health Advisor", "is_disqualified": true, "stars": 0, "score_impact": 1.9, "score_meta_tooling": 0.8, "score_tech_depth": 1.3, "score_demo": 1.4, "score_total": 2.16, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "High-impact domain", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Muse Spark integration", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (47)", "+0.4" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Live web deployment", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 850, "is_new": false, "commits_delta": 39, "rank_delta": -315, "commits_delta_last_run": 0 }, { "full_name": "seyfelislam/ECHKILI-Meta-Hackathon-2026", "html_url": "https://github.com/seyfelislam/ECHKILI-Meta-Hackathon-2026", "track": "Build for Your World", "domain": "Robotics, IoT & Manufacturing", "summary": "Fictional vehicle-cabin diagnostics demo with evidence tracing", "readme_summary": "Offline-first fictional diagnostics demo showing observation selection, evidence graph, contradiction detection and human review. Three-step judge flow with before/after trace. No real diagnosis or Meta calls in demo.", "tech_highlights": [ "Evidence Graph", "Safety-Aware AI", "Offline Demo Harness" ], "created_at": "2026-10-26T16:40:38Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 12, "commits_before_window": 0, "prs_total": 4, "prs_merged": 2, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": false, "has_ci": true, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": true, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Medical Advice / Diagnostic (Banned Anti-Project)", "is_disqualified": true, "stars": 0, "score_impact": 2.0, "score_meta_tooling": 1.6, "score_tech_depth": 1.2, "score_demo": 0.6, "score_total": 2.16, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "High-impact domain", "+0.4" ], [ "Eval & benchmark proof", "+0.3" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "5+ window commits (12)", "+0.2" ], [ "Automated test suite", "+0.3" ], [ "Agent / eval harness", "+0.2" ], [ "Automated CI workflow", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 851, "is_new": false, "commits_delta": 0, "rank_delta": -314, "commits_delta_last_run": 0 }, { "full_name": "jacob222222/welcome-fillseats-ai", "html_url": "https://github.com/jacob222222/welcome-fillseats-ai", "track": "Build for Your World", "domain": "Business, Sales & Commerce", "summary": "Multilingual night-time enrollment agent to fill empty childcare seats.", "readme_summary": "Agent workflow for Minnesota childcare providers handling after-hours inquiries, tour booking and enrollment forms. Built with Next.js using Muse Code, with Somali and Spanish support and privacy-safe flyer flow.", "tech_highlights": [ "Muse Models", "Next.js App", "Multilingual Agent" ], "created_at": "2026-10-26T16:50:25Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 10, "commits_before_window": 0, "prs_total": 2, "prs_merged": 2, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": true, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Banned Medical / Health Advisor", "is_disqualified": true, "stars": 0, "score_impact": 1.8, "score_meta_tooling": 1.8, "score_tech_depth": 0.8, "score_demo": 1.0, "score_total": 2.16, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Multi-module scope (>10 files)", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ] ], "tech": [ [ "Base", "+0.3" ], [ "5+ window commits (10)", "+0.2" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 852, "is_new": false, "commits_delta": 4, "rank_delta": -320, "commits_delta_last_run": 0 }, { "full_name": "pepemxl/meta-ai-hackathon-2026", "html_url": "https://github.com/pepemxl/meta-ai-hackathon-2026", "track": "Build for Your World", "domain": "Multimodal Vision & Video (SAM / Vision)", "summary": "Phone-recorded soccer tracking converted to meters with tactical reports", "readme_summary": "Coach records match on one phone, marks pitch once for homography calibration. Worker uses SAM 3.1 to track players and ball in meters despite pan and poor light. Muse Spark writes tactical report.", "tech_highlights": [ "SAM 3.1 Vision", "Muse Spark", "Homography Tracking" ], "created_at": "2026-10-26T18:22:40Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 78, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": false, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Banned Sports Coach/Analyzer", "is_disqualified": true, "stars": 0, "score_impact": 1.6, "score_meta_tooling": 1.6, "score_tech_depth": 0.9, "score_demo": 1.0, "score_total": 2.04, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (78)", "+0.6" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 853, "is_new": false, "commits_delta": 43, "rank_delta": -312, "commits_delta_last_run": 0 }, { "full_name": "sunwen1983/fixlens", "html_url": "https://github.com/sunwen1983/fixlens", "track": "Build for Your World", "domain": "Multimodal Vision & Video (SAM / Vision)", "summary": "Photo of home fault segmented and diagnosed into repair checklist and draft ticket", "readme_summary": "Uploads a home fault photo, highlights faulty area with SAM 3.1 segmentation, then diagnoses type, severity and cause. Generates ordered checklist, parts list and DRAFT landlord-tenant ticket. Uses Muse Spark for reasoning with safety-first warnings.", "tech_highlights": [ "SAM 3.1 Vision", "Muse Spark 1.3", "Python + Tests" ], "created_at": "2026-10-26T18:50:11Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 16, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Banned Simple Image Analyzer", "is_disqualified": true, "stars": 0, "score_impact": 1.6, "score_meta_tooling": 1.6, "score_tech_depth": 1.3, "score_demo": 0.6, "score_total": 2.04, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (16)", "+0.4" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 854, "is_new": false, "commits_delta": 0, "rank_delta": -321, "commits_delta_last_run": 0 }, { "full_name": "chiheb-Ben/MetaSpace-AI", "html_url": "https://github.com/chiheb-Ben/MetaSpace-AI", "track": "Push the Frontier", "domain": "Robotics, IoT & Manufacturing", "summary": "Real-time zero-G station sim with AI flight director for astronaut training", "readme_summary": "Unreal Engine 5.7 C++ 6-DOF physics sim where Meta AI acts as Flight Director perceiving telemetry and computing risk. Uses Muse Spark 1.3 via Meta Model API for cyber-physical control.", "tech_highlights": [ "Unreal Engine 5.7", "Muse Spark 1.3", "6-DOF Physics Sim" ], "created_at": "2026-10-29T22:05:39Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 9, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": false, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": true, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Banned Basic RAG", "is_disqualified": true, "stars": 1, "score_impact": 2.4, "score_meta_tooling": 1.3, "score_tech_depth": 0.7, "score_demo": 0.6, "score_total": 2.0, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "High-impact domain", "+0.4" ], [ "Eval & benchmark proof", "+0.3" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "5+ window commits (9)", "+0.2" ], [ "Agent / eval harness", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 855, "is_new": true, "commits_delta": 9, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "quanticomp/living-record", "html_url": "https://github.com/quanticomp/living-record", "track": "Push the Frontier", "domain": "Education & Knowledge Systems", "summary": "Queryable recording estate that returns computed or fabrication-gated answers", "readme_summary": "System for owners of meeting/call recording estates needing checkable answers. Deterministic computation over records or Muse Wonder synthesis through fabrication gate. Answer states computed vs reasoned with receipts, plus eval harness.", "tech_highlights": [ "Muse Wonder 1.0", "Deterministic Compute", "Eval Harness" ], "created_at": "2026-10-26T19:24:43Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 20, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": false, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Banned Basic RAG", "is_disqualified": true, "stars": 0, "score_impact": 2.0, "score_meta_tooling": 1.6, "score_tech_depth": 0.7, "score_demo": 0.6, "score_total": 1.96, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "Domain alignment", "+0.3" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "15+ window commits (20)", "+0.4" ] ], "demo": [ [ "Base", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 856, "is_new": false, "commits_delta": 0, "rank_delta": -314, "commits_delta_last_run": 0 }, { "full_name": "Wauguzi/tabibu", "html_url": "https://github.com/Wauguzi/tabibu", "track": "Build for Your World", "domain": "Healthcare, Civic Tech & Sustainability", "summary": "Connects Nairobi patients, doctors and pathologists in English and Kiswahili", "readme_summary": "Flutter app on iOS, Android and web backed by Firebase. Patients book nearby doctors, doctors manage days and MDT consults, pathologists sign AI-pre-read cases. AI pre-reads and outbreak drafts run behind Cloud Functions, human always decides.", "tech_highlights": [ "Flutter + Firebase", "Cloud Functions AI", "EN + Kiswahili UX" ], "created_at": "2026-10-26T17:25:19Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 144, "commits_before_window": 0, "prs_total": 6, "prs_merged": 1, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": true, "has_ci": true, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Medical Advice / Diagnostic (Banned Anti-Project)", "is_disqualified": true, "stars": 1, "score_impact": 1.6, "score_meta_tooling": 0.5, "score_tech_depth": 1.9, "score_demo": 0.8, "score_total": 1.92, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "High-impact domain", "+0.4" ], [ "Multi-module scope (>10 files)", "+0.2" ] ], "meta": [ [ "Base", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (144)", "+0.6" ], [ "Automated test suite", "+0.3" ], [ "Modular src/ architecture", "+0.3" ], [ "Automated CI workflow", "+0.2" ], [ "PR review workflow (1 PRs)", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ] ] }, "rank": 857, "is_new": false, "commits_delta": 119, "rank_delta": -312, "commits_delta_last_run": 0 }, { "full_name": "fatguylilcoat98/lylo-mechanic-hackathon", "html_url": "https://github.com/fatguylilcoat98/lylo-mechanic-hackathon", "track": "Build for Your World", "domain": "General & Emerging Applications", "summary": "Explains car OBD codes in plain language and flags if safe to drive", "readme_summary": "Android app that reads OBDLink CX/MX+ codes, live data and readiness monitors with evidence for claims. Works without adapter via user-reported symptoms. Uses Meta Muse for plain-language diagnosis built during hackathon.", "tech_highlights": [ "Android + OBDLink", "Meta Muse", "Evidence-based Dx" ], "created_at": "2026-10-26T13:28:06Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 55, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": true, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Medical Advice / Diagnostic (Banned Anti-Project)", "is_disqualified": true, "stars": 0, "score_impact": 1.5, "score_meta_tooling": 0.8, "score_tech_depth": 1.2, "score_demo": 1.0, "score_total": 1.8, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "General domain", "+0.2" ], [ "Detailed problem docs (>5 KB)", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Muse Spark integration", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "50+ window commits (55)", "+0.6" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ], [ "Visual docs & diagrams (>6 KB)", "+0.2" ] ] }, "rank": 858, "is_new": false, "commits_delta": 0, "rank_delta": -314, "commits_delta_last_run": 0 }, { "full_name": "nothariharan/fasal-doctor", "html_url": "https://github.com/nothariharan/fasal-doctor", "track": "Build for Your World", "domain": "Healthcare, Civic Tech & Sustainability", "summary": "Crop doctor measuring leaf damage and checking pesticide labels for Indian farmers.", "readme_summary": "Farmer sends leaf photo with scale card plus Hindi/Tamil/Telugu/Marathi voice note. SAM 3.1 masks lesions to measure affected area; Muse Spark reads pesticide label dose and interval to flag overdosing. Re-measures same leaves on day 3-5 to advise respray.", "tech_highlights": [ "SAM 3.1 Vision", "Muse Spark", "Multilingual Voice" ], "created_at": "2026-10-26T08:03:09Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 2, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": false, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": true, "has_eval_benchmarks": false, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Medical Advice / Diagnostic (Banned Anti-Project)", "is_disqualified": true, "stars": 0, "score_impact": 1.4, "score_meta_tooling": 2.3, "score_tech_depth": 0.3, "score_demo": 0.4, "score_total": 1.76, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "High-impact domain", "+0.4" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ], [ "Open-weights / fine-tuning", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ] ] }, "rank": 859, "is_new": false, "commits_delta": 0, "rank_delta": -310, "commits_delta_last_run": 0 }, { "full_name": "sajjadbdai/ledgerlens", "html_url": "https://github.com/sajjadbdai/ledgerlens", "track": "Build for Your World", "domain": "Finance, Crypto & Web3", "summary": "Converts supplier invoices and statements into validated accounting ledgers", "readme_summary": "Ingests PDF/photo invoices and extracts vendor, line items, VAT and totals using SAM 3.1 for regions and Muse for handwriting. Python validator checks arithmetic like discounts and advances before ledger export.", "tech_highlights": [ "SAM 3.1 Vision", "Muse Vision", "Python Validator" ], "created_at": "2026-10-29T16:39:19Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 6, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": false, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Banned Basic RAG", "is_disqualified": true, "stars": 0, "score_impact": 1.3, "score_meta_tooling": 1.8, "score_tech_depth": 0.5, "score_demo": 0.4, "score_total": 1.6, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ], [ "3+ Meta model pipeline", "+0.2" ] ], "tech": [ [ "Base", "+0.3" ], [ "5+ window commits (6)", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ] ] }, "rank": 860, "is_new": true, "commits_delta": 6, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "ashrafulislamse/renalradar", "html_url": "https://github.com/ashrafulislamse/renalradar", "track": "Build for Your World", "domain": "Healthcare, Civic Tech & Sustainability", "summary": "Camera and voice meal companion helping kidney patients document dishes.", "readme_summary": "Next.js PWA that segments dishes with SAM 3.1 and identifies foods with Muse Spark. Provides cited nutrient literacy, documentation-only with no medical advice enforced. Focused on Southeast Asian diets for CKD patients.", "tech_highlights": [ "SAM 3.1 Vision", "Muse Spark", "Next.js PWA" ], "created_at": "2026-10-29T18:55:40Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 4, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": true, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Banned Medical / Health Advisor", "is_disqualified": true, "stars": 0, "score_impact": 1.4, "score_meta_tooling": 1.6, "score_tech_depth": 0.6, "score_demo": 0.4, "score_total": 1.6, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "High-impact domain", "+0.4" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ], [ "SAM 3.1 / Multimodal Muse", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "Modular src/ architecture", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ] ] }, "rank": 861, "is_new": true, "commits_delta": 4, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "ThakhinBo/dharmavera-hackathon", "html_url": "https://github.com/ThakhinBo/dharmavera-hackathon", "track": "Build for Your World", "domain": "Gaming, Entertainment & Creative Media", "summary": "Numerology app that draws 7-oracle scores, charts and AI guidance", "readme_summary": "PHP/JS fortune app at southrule.com/?demo=1, tap 4 numbers to get Mahabote score, seven oracle scores, remedy, wave and lifeline charts. Hackathon work adds overall remedy and AI guidance sentence on top of older 7-oracle engine.", "tech_highlights": [ "PHP + JavaScript", "7-Oracle Engine", "Muse Guidance" ], "created_at": "2026-10-26T08:46:13Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 4, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": true, "has_src": false, "has_ci": false, "meta_api_verified": true, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Banned Medical / Health Advisor", "is_disqualified": true, "stars": 0, "score_impact": 1.4, "score_meta_tooling": 1.3, "score_tech_depth": 0.6, "score_demo": 0.4, "score_total": 1.48, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "General domain", "+0.2" ], [ "Multi-module scope (>10 files)", "+0.2" ] ], "meta": [ [ "Base", "+0.5" ], [ "Meta Model API / SDK", "+0.5" ], [ "Muse Spark integration", "+0.3" ] ], "tech": [ [ "Base", "+0.3" ], [ "Automated test suite", "+0.3" ] ], "demo": [ [ "Base", "+0.4" ] ] }, "rank": 862, "is_new": false, "commits_delta": 1, "rank_delta": -315, "commits_delta_last_run": 0 }, { "full_name": "altima261/trifecta-checker", "html_url": "https://github.com/altima261/trifecta-checker", "track": "Push the Frontier", "domain": "Developer Tooling, Infra & Security", "summary": "One-call API safety gate that blocks risky agent actions before data theft happens", "readme_summary": "Checks AI agent tool calls for Lethal Trifecta risk via hosted API and demo UI. TypeScript SDK for easy integration plus Concordium ID for verifiable trusted agents. Built as verifiable agent security gateway.", "tech_highlights": [ "Agent Safety API", "TypeScript SDK", "Concordium ID" ], "created_at": "2026-11-01T06:03:28Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 5, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": false, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": false, "has_video_demo": false, "video_urls": [], "has_live_deploy": true, "live_urls": [ "https://trifecta-checker.vercel.app/", "https://trifecta-checker.vercel.app/api/check-trifecta" ], "anti_project_flag": "Banned Political / Defense Policy", "is_disqualified": true, "stars": 0, "score_impact": 1.8, "score_meta_tooling": 0.5, "score_tech_depth": 0.5, "score_demo": 0.8, "score_total": 1.44, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Track 2 (Push the Frontier)", "+0.4" ], [ "High-impact domain", "+0.4" ] ], "meta": [ [ "Base", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "5+ window commits (5)", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Live web deployment", "+0.4" ] ] }, "rank": 863, "is_new": true, "commits_delta": 5, "rank_delta": 0, "commits_delta_last_run": 0 }, { "full_name": "phanidileep4/findit", "html_url": "https://github.com/phanidileep4/findit", "track": "Build for Your World", "domain": "Multimodal Vision & Video (SAM / Vision)", "summary": "Glasses-linked visual memory to recall where everyday objects were seen", "readme_summary": "Planning scaffold for Ray-Ban Meta Gen 2 and iPhone object recall. Proposes Meta multimodal model to extract object labels and scene context from intentional captures. No runnable app yet; iPhone storage, search and verification planned.", "tech_highlights": [ "Ray-Ban Meta Gen 2", "Meta Multimodal AI", "iPhone Client Concept" ], "created_at": "2026-10-28T04:07:16Z", "is_multi_repo": false, "repo_count": 1, "linked_repos": [], "commits_in_window": 7, "commits_before_window": 0, "prs_total": 0, "prs_merged": 0, "is_preexisting": false, "has_docker": false, "has_tests": false, "has_src": false, "has_ci": false, "meta_api_verified": false, "partner_infra": "Direct", "open_weights_tuning": false, "has_eval_benchmarks": false, "has_setup_guide": true, "has_video_demo": false, "video_urls": [], "has_live_deploy": false, "live_urls": [], "anti_project_flag": "Banned Basic RAG", "is_disqualified": true, "stars": 0, "score_impact": 1.3, "score_meta_tooling": 0.5, "score_tech_depth": 0.5, "score_demo": 0.8, "score_total": 1.24, "score_breakdown": { "impact": [ [ "Base hackathon repo", "+1.0" ], [ "Domain alignment", "+0.3" ] ], "meta": [ [ "Base", "+0.5" ] ], "tech": [ [ "Base", "+0.3" ], [ "5+ window commits (7)", "+0.2" ] ], "demo": [ [ "Base", "+0.4" ], [ "Reproducible setup guide", "+0.4" ] ] }, "rank": 864, "is_new": false, "commits_delta": 0, "rank_delta": -314, "commits_delta_last_run": 0 } ]